Intel Xeon D-2700 series NAS (512 GB) vs Intel Arc A580 for local AI
Pick two to four systems or devices to see which runs more models, faster, for the kind of work you do.
Winner: Intel Xeon D-2700 series NAS (512 GB)
For general chat: It runs 156 more LLMs (614 vs 458). On the other hand, the Intel Arc A580 is about 22.8× faster on its own top models.
 Intel Xeon D-2700 series NAS (512 GB)
|
 Intel Arc A580
|
|
|---|---|---|
| Memory | 512 GB unified | 8.0 GB VRAM |
| Usable for models | 471 GB | 8.0 GB |
| Memory bandwidth | 51 GB/s | 512 GB/s |
| FP16 compute | 0.6 TFLOPS | 24.6 TFLOPS |
| Launch price | — | $179 |
| Released | 2022 | 2023 |
| LLMs that run | 614 of 619 | 458 of 619 |
| LLMs that run well | 316 | 337 |
| Image models that run | 60 of 60 | 49 of 60 |
| Video models that run | 43 of 43 | 7 of 43 |
| Decision models that run | 70 of 70 | 65 of 70 |
| Top-10 LLM average score | 87 | 91 |
| Top-10 LLM average speed | 2.5 tok/s | 57.3 tok/s |
| Best LLM | GLM-4.7 (355B-A32B) | K2 Horizon 7B |
Highlighted values are the best of the two. Model results assume 8K of context and the default macOS GPU memory limit on Macs.
LLMs
614 of 619 LLMs run on the Intel Xeon D-2700 series NAS (512 GB). 471 GB usable for models.
458 of 619 LLMs run on the Intel Arc A580. 8.0 GB usable for models.
| Model | QualityXeon D-2700 series NAS | SpeedXeon D-2700 series NAS | RunsXeon D-2700 series NAS | QualityArc A580 | SpeedArc A580 | RunsArc A580 |
|---|---|---|---|---|---|---|
| GLM-4.7 (355B-A32B) | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4 Flash (284B-A13B) | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax M2.7 (230B-A10B) | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3 Ultra 550B-A55B | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3.2 (671B) | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiMo V2.6 Flash (310B-A15B) | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax M2.5 (230B-A10B) | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Inkling Small (276B-A12B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3.2 Exp | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax M2.1 (230B-A10B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek R1 (671B) | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Naive N0.5 Flash (309B-A15.5B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4.1 Flash 1017 (552B-A16B) | 82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slowtight fit | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3.1 Terminus | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Step 3.7 Flash (198B-A11B) | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiMo V2.5 (310B-A15B) | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3.1 (671B) | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| InternVL3.5 241B-A28B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4.1 Flash (552B-A16B) | 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slowtight fit | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax M2 (230B-A10B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Step 3.5 Flash (196B-A11B) | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral Large 3 (675B) | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slowtight fit | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-4.6 (355B-A32B) | 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Llama 3.1 Nemotron Ultra 253B v1 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiMo V2 Flash (309B-A15B) | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-5.3 (753B-A40B) | 82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-4.5 (355B-A32B) | 81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax-M1 80K | 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-5.2 (753B-A40B) | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Muse Spark Open (816B-A42B) | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax-M1 40K | 79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-5.1 (744B-A40B) | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Hunyuan Hy4 Preview (780B) | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slowtight fit | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.6 35B-A3B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| GLM-5 (744B-A40B) | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniCPM-V 4.7 35B-A3B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 32.9 tok/s | Slowheavy RAM offload |
| ERNIE 4.5 300B-A47B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 35B-A3B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| Ornith 1.5 122B-A10B | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kolibri 1 (78B-A3.5B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.6 tok/s | Runs well | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 122B-A10B | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 Coder 480B-A35B | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3 0324 (671B) | 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Solar Open 2 250B | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nex N2 Mini (35B-A3B) | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Slowheavy RAM offload |
| Intern-S2 (397B-A17B) | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 397B-A17B | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nex N2 Pro (397B-A17B) | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Flint (40B-A2.5B) | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 19.0 tok/s | Runs well | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 37.2 tok/s | Slowheavy RAM offload |
| Sage-A1.5 35B-A3B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| Ornith 1.5 397B-A17B | 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3.5 Super VL 120B-A12B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek R1 0528 (671B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-Next 80B-A3B Thinking | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4 Flash (April 2026) | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ornith 1.5 35B-A3B | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| Hermes 4 405B | 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Apodex 1.1 Mini (35B-A3B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| Ornith 1.0 35B-A3B | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Slowheavy RAM offload |
| Gemma 4 26B-A4B | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 10.6 tok/s | Runs well | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 29.7 tok/s | Slowheavy RAM offload |
| Nemotron 3.5 Bolt 74B-A9B | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-5.3 Flash (320B-A18B) | 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| gpt-oss 120B | 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax-Text-01 | 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.8 Flash Next (125B-A6B) | 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-4.7 Flash (30B-A3B) | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 33.8 tok/s | Slowheavy RAM offload |
| Agents-A1 35B-A3B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Slowheavy RAM offload |
| Qwen AgentWorld 35B-A3B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 33.1 tok/s | Slowheavy RAM offload |
| Qwen3 Next 80B-A3B Instruct | 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Tülu 3 405B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Trinity Large Thinking (400B-A13B) | 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Hunyuan Hy3 (295B-A21B) | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3 Super 120B-A12B | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V3 (671B) | 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 1.4 tok/s | Very slowtight fit | 52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nanbeige4.3 33B | 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 0.8 tok/s | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Qwen3.8 27B | 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Step 5 Preview (600B-A27B) | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Raon-1 mini Preview (30B-A4B) | 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well | 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 25.8 tok/s | Slowheavy RAM offload |
| Ling 3.1 Flash 1019 (560B-A25B) | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiMo V2.6 Pro (1T-A42B) | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 tok/s | Very slowtight fit | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi K2.6 (1T) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.6 27B | 94Excellent quality (A+) · 94 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Llama 3.1 405B Instruct | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Jamba 1.5 Large | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi K2.5 (1T) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 27B | 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Ling 3.1 Flash (560B-A25B) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Laguna XS 2.1 (33B-A3B) | 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 31.7 tok/s | Slowheavy RAM offload |
| MiMo V2.5 Pro (1T-A42B) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral Large 4 (1T-A52B) | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Muse Glimmer 30B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Inkling (975B-A41B) | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 tok/s | Very slowtight fit | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| KAT-Coder V2.5 Dev (35B-A3B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 33.1 tok/s | Slowheavy RAM offload |
| Gemma 4 31B | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 0.8 tok/s | Very slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Kimi K2 Instruct 0905 (1T) | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 Coder Next (80B-A3B) | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-4.6V | 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral Medium 3.5 (128B) | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Beam 1.0 (501B-A23B) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ling 2.6 1T | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 1.3 tok/s | Very slowtight fit | 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi K2 Instruct (July 2025) | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron Cascade 2 30B-A3B | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 tok/s | Runs well | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 30.0 tok/s | Slowheavy RAM offload |
| NorthCUA Pro | 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral Large 2.1 (2411) | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ling 1T | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 tok/s | Very slowtight fit | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax M3.1 Flash (428B-A23B) | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-4.5V | 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Solar Open 100B | 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Command A (111B) | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 30B-A3B Instruct 2507 | 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 30.7 tok/s | Slowheavy RAM offload |
| LongCat Flash Chat (560B) | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LFM2.5 24B-A2B | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 19.3 tok/s | Runs well | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 94.5 tok/s | Runs welloffloads to RAM |
| Pixtral Large 124B (2411) | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral Large 2 (123B) | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3 Nano 30B-A3B | 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 tok/s | Runs well | 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 30.0 tok/s | Slowheavy RAM offload |
| Kimi Linear 48B-A3B | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 40.3 tok/s | Slowheavy RAM offload |
| MiniMax M3 (427B) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-VL 30B-A3B Thinking | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 30.5 tok/s | Slowheavy RAM offload |
| Ling 3.0 Flash (127B-A5B) | 68Good quality (B) · 68 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DiffusionGemma 26B-A4B IT | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 tok/s | Runs well | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 28.4 tok/s | Slowheavy RAM offload |
| GLM-4.5 Air (106B-A12B) | 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Sarvam 105B | 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Hunyuan Hy-Memory 30B-A3B | 84Great quality (A) · 84 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 80Great quality (A) · 80 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 33.6 tok/s | Slowheavy RAM offload |
| K2-Horizon (375B-A23B) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-VL 30B-A3B Instruct | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 30.5 tok/s | Slowheavy RAM offload |
| dots.llm1 Instruct | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 30B-A3B | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 30.7 tok/s | Slowheavy RAM offload |
| Llama 4 Maverick (17B x 128E) | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Sarvam 30B | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 tok/s | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 41.3 tok/s | Slowheavy RAM offload |
| Devstral 2 (123B) | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3.5 Lightning 30B-A3B | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 34.4 tok/s | Slowheavy RAM offload |
| Gemma 4 12B | 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 51.9 tok/s | Runs welltight fit |
| gpt-oss 20B | 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 14.3 tok/s | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 39.9 tok/s | Slowheavy RAM offload |
| Mistral Small 4 (119B-A6B) | 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| EXAONE 4.5 33B | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 0.8 tok/s | Very slow | 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| K2 Horizon 7B | 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 53.3 tok/s | Runs welltight fit |
| Kimi K2.7 Code (1T) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Llama 3.3 Nemotron Super 49B v1.5 | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi K2 Thinking (1T) | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit | 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-Omni 30B-A3B Instruct | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 29.4 tok/s | Slowheavy RAM offload |
| Seed-OSS 36B Instruct | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow | 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slowheavy RAM offload |
| Ling 3.0 Tiny (8B-A1.3B) | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 34.4 tok/s | Runs great | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 133 tok/s | Runs welltight fit |
| SenseNova Loop 9B Preview | 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 49.7 tok/s | Runs welltight fit |
| North Mini Code 1.0 (30B-A3B) | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 34.4 tok/s | Slowheavy RAM offload |
| Hermes 4.3 36B | 79Great quality (A) · 79 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow | 66Good quality (B) · 66 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slowheavy RAM offload |
| Hunyuan A13B (80B-A13B) | 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ornith 1.5 9B | 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 49.8 tok/s | Runs welltight fit |
| Qwen3-VL 32B Instruct | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.8 tok/s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 tok/s | Slowheavy RAM offload |
| InternVL3 78B | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ling Flash 2.0 (100B-A6B) | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Command A Reasoning (111B) | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 9B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 49.8 tok/s | Runs welltight fit |
| Maple Preview (20B-A1B) | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 30.5 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 157 tok/s | Runs welloffloads to RAM |
| Llama 3.3 70B Instruct | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Hermes 4 70B | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Trinity Mini (26B-A3B) | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 37.1 tok/s | Slowheavy RAM offload |
| Qwen3 30B-A3B Thinking 2507 | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 30.7 tok/s | Slowheavy RAM offload |
| Qwen3 Coder 30B-A3B | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 tok/s | Runs well | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 30.7 tok/s | Slowheavy RAM offload |
| Ornith 1.0 9B | 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 49.8 tok/s | Runs welltight fit |
| InternVL3.5 38B | 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| Qwen2.5-VL 72B Instruct | 73Great quality (A) · 73 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Command R+ (08-2024) 104B | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen2.5 72B Instruct | 73Great quality (A) · 73 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nemotron 3.5 Bolt E4B | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 74.0 tok/s | Runs welltight fit |
| TMax 9B | 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 53.6 tok/s | Runs great |
| Gemma 4 E2B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 22.0 tok/s | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 106 tok/s | Runs great |
| Granite 4.2 30B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slowheavy RAM offload |
| Qwen3 32B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Nemotron Labs Dory 1.0 4B | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 12.7 tok/s | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 61.4 tok/s | Runs great |
| DeepSeek R1 Distill Llama 70B | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Tülu 3 70B | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 235B-A22B Instruct 2507 | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Nanbeige4.2 3B | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 tok/s | Runs well | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 79.9 tok/s | Runs great |
| ERNIE 4.5 21B-A3B | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 85.7 tok/s | Runs welloffloads to RAM |
| Qwen3-VL 235B-A22B Instruct | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Gemma 4 E4B | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 74.0 tok/s | Runs welltight fit |
| Ling 3.0 flash Sante | 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V2.5 1210 | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Axion 1.0 35B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Slowheavy RAM offload |
| Groot 65B A6B 261023 | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 235B-A22B | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Grok-1 (314B) | 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| K-EXAONE 236B-A23B | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LFM3 1.7B | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 29.3 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 65.1 tok/s | Runs great |
| GLM-4 32B 0414 | 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Llama 3.1 70B Instruct | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Spark-X2.6 4B | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 59.5 tok/s | Runs great |
| MiniCPM5 2B | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 20.1 tok/s | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 44.7 tok/s | Runs great |
| Command A+ (218B-A25B) | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi Dev 72B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V2.5 | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ling Mini 2.0 (16B-A1.4B) | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 204 tok/s | Runs welltight fit |
| Granite 4.1 30B | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slowheavy RAM offload |
| QVQ 72B Preview | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Olmo 3.1 32B Instruct | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| EXAONE 4.0 32B | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| Hermes 3 (Llama 3.1 70B) | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| NorthCUA Mini | 56Good quality (B) · 56 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Slowheavy RAM offload |
| Llama 3.2 90B Vision Instruct | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Baichuan M3 235B-A22B | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Apriel 1.5 15B Thinker | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 18.4 tok/s | Runs welloffloads to RAM |
| Kimi-VL A3B Thinking 2506 | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 144 tok/s | Runs welltight fit |
| Mellum2.1 Thinking (12B-A2.5B) | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 19.0 tok/s | Runs well | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 138 tok/s | Runs welltight fit |
| LFM2.5 8B-A1B | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 30.3 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 154 tok/s | Runs great |
| Command R+ 104B (04-2024) | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Granite 4.2 8B | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slow | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 54.6 tok/s | Runs welltight fit |
| LFM2 24B-A2B | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 tok/s | Runs well | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 99.3 tok/s | Runs welloffloads to RAM |
| Ling 2.6 Flash (104B-A7.4B) | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| InternVL3 38B | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| ERNIE 4.5 21B-A3B Thinking | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 86.2 tok/s | Runs welloffloads to RAM |
| Qwen2.5 32B Instruct | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Baichuan M2 32B | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Snowflake Arctic Instruct | 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Apertus v1.5 70B | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Llama 3.1 Nemotron 70B Instruct | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Phi-4 Reasoning Vision 15B | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 17.3 tok/s | Runs welloffloads to RAM |
| MiMo V2.6 Distill Qwen 9B | 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 42.1 tok/s | Runs welltight fit |
| Ring Flash 2.0 (100B-A6B) | 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Llama 4 Scout 17B-16E | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.5 4B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 52.4 tok/s | Runs great |
| TMax 4B | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 12.0 tok/s | Runs well | 61Good quality (B) · 61 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 58.1 tok/s | Runs great |
| Groot 19B A3B 261023 | 54Fair quality (C) · 54 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 68.0 tok/s | Runs welloffloads to RAM |
| Qwen2.5-VL 32B Instruct | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 tok/s | Slowheavy RAM offload |
| Qwen2-VL 72B Instruct | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen2 72B Instruct | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Terminal RSI 27B | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 1.3 tok/s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Granite 4.0 H Tiny (7B-A1B) | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 43.3 tok/s | Runs great | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 151 tok/s | Runs great |
| Leanstral 119B-A6B | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3 14B | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 43.8 tok/s | Runs welloffloads to RAM |
| Agents-A1 4B | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 53.8 tok/s | Runs great |
| QwQ 32B | 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| LFM3-VL 2B | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 26.4 tok/s | Runs well | 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 58.7 tok/s | Runs great |
| Granite 4.0 H Small (32B-A9B) | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Slowheavy RAM offload |
| DeepSeek V2 Chat | 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Hermes 4 14B | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 44.3 tok/s | Runs welloffloads to RAM |
| TMax 27B | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Qwen3 235B-A22B Thinking 2507 | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Fara 1.5 4B | 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 53.8 tok/s | Runs great |
| InternVL3.5 8B | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 56.3 tok/s | Runs welltight fit |
| DeepSeek Coder V2 (236B) | 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-VL 8B Instruct | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 54.7 tok/s | Runs welltight fit |
| OpenReasoning Nemotron 32B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Skywork OR1 32B | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Olmo 3.1 32B Think | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| Mixtral 8x22B Instruct | 54Fair quality (C) · 54 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 0.9 tok/s | Very slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Fara 1.5 27B | 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Ministral 3 14B | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 56.5 tok/s | Runs welltight fit |
| Falcon-H1 34B Instruct | 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Phi-4 (14B) | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 36.7 tok/s | Runs welloffloads to RAM |
| Apertus 70B Instruct | 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| InternVL3 14B | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 17.6 tok/s | Runs welloffloads to RAM |
| DeepSeek Coder V2 Instruct (0614) | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Laguna S 2.1 (118B-A8B) | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniCPM-V 4.5 8B | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 55.2 tok/s | Runs welltight fit |
| Mage-VL 4.7B | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 tok/s | Runs well | 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 70.3 tok/s | Runs great |
| Granite 4.1 8B | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 54.6 tok/s | Runs welltight fit |
| EXAONE Deep 32B | 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 4.4 tok/s | Slowheavy RAM offload |
| Nemotron Nano 9B v2 | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 54.0 tok/s | Runs great |
| UI-Mate 27B | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow | 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| GLM-Z1 32B (0414) | 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Qwen3 4B Instruct 2507 | 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 12.6 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 60.8 tok/s | Runs great |
| GLM-4.1V 9B Thinking | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 46.7 tok/s | Runs welltight fit |
| Command R (08-2024) 32B | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Qwen2.5 14B Instruct | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 38.1 tok/s | Runs welloffloads to RAM |
| Kimi-VL A3B Instruct | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 144 tok/s | Runs welltight fit |
| Llama 3 70B Instruct | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3-VL 4B Instruct | 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 53Fair quality (C) · 53 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 75.0 tok/s | Runs great |
| Granite 4.2 3B | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 tok/s | Runs well | 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 66.8 tok/s | Runs great |
| UI-Mate 9B | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 42.1 tok/s | Runs welltight fit |
| UI-Venus 2 9B | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 42.1 tok/s | Runs welltight fit |
| Gemma 3 12B IT | 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 50.9 tok/s | Runs welltight fit |
| DeepSeek R1 Distill Qwen 32B | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Phi-4 Reasoning Plus (14B) | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 18.7 tok/s | Runs welloffloads to RAM |
| MiniCPM-V 4.7 1B | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Runs great | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 72.7 tok/s | Runs great |
| Aya Vision 32B | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Aya Expanse 32B | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Qwen2.5 14B Instruct 1M | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| OLMo 2 32B Instruct | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| MiniCPM5 1B | 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 38.7 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 104 tok/s | Runs great |
| Qwen1.5 110B Chat | 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 0.2 tok/s | Very slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ministral 3 8B | 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 53.8 tok/s | Runs welltight fit |
| OpenHands LM 32B | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| Qwen3 4B | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 12.6 tok/s | Runs well | 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 60.8 tok/s | Runs great |
| Nemotron 3 Nano 4B | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 12.8 tok/s | Runs well | 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 61.6 tok/s | Runs great |
| Phi-4 Reasoning (14B) | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 18.7 tok/s | Runs welloffloads to RAM |
| Unlimited OCR 2 (3B-A0.6B) | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 48.3 tok/s | Runs great | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 160 tok/s | Runs great |
| North Micro Vision | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 20.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 98.6 tok/s | Runs great |
| Moonlight 16B-A3B Instruct | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 16.0 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 144 tok/s | Runs welltight fit |
| LFM2 8B-A1B | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 30.3 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 154 tok/s | Runs great |
| TMax 2B | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 26.9 tok/s | Runs well | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 59.9 tok/s | Runs great |
| LFM2.5 2.6B | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 18.8 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 41.7 tok/s | Runs great |
| Granite 4.1 3B | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 14.9 tok/s | Runs well | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 71.9 tok/s | Runs great |
| Devstral Small 2 (24B) | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Qwen2.5 Coder 32B Instruct | 66Good quality (B) · 66 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| LFM2.5 1.2B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 43.3 tok/s | Runs great | 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 96.3 tok/s | Runs great |
| Nous Hermes 2 Mixtral 8x7B DPO | 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Slowheavy RAM offload |
| Mage-VL-Cowork 4.7B | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 tok/s | Runs well | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 70.3 tok/s | Runs great |
| LFM2.5-VL 3B | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 16.2 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 78.3 tok/s | Runs great |
| PaddleOCR-VL 1.6 0.9B | 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 43.6 tok/s | Runs great | 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs great |
| Qwen3.5 2B | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 22.3 tok/s | Runs well | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 49.6 tok/s | Runs great |
| Command R 35B (v01) | 53Fair quality (C) · 53 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Gemma 3n E4B | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 12.7 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 99.2 tok/s | Runs great |
| Jamba Reasoning 3B | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 76.4 tok/s | Runs great |
| QwQ 32B Preview | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | Slowheavy RAM offload |
| MiniCPM-o 2.6 8B | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 tok/s | Slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 55.4 tok/s | Runs great |
| DeepSeek Coder V2 Lite (16B) | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 162 tok/s | Runs welltight fit |
| Ministral 3 14B Reasoning | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 56.5 tok/s | Runs welltight fit |
| GLM-4 9B 0414 | 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 51.1 tok/s | Runs welltight fit |
| NorthCUA Nano | 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 42.1 tok/s | Runs welltight fit |
| AceReason Nemotron 14B | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| OpenReasoning Nemotron 14B | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| Qwen2.5 Coder 14B Instruct | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| DeepSeek V2 Lite Chat | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 tok/s | Runs well | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 162 tok/s | Runs welltight fit |
| Apriel Nemotron 15B Thinker | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 17.8 tok/s | Runs welloffloads to RAM |
| Jamba 1.5 Mini | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Slowheavy RAM offload |
| Falcon 3 10B Instruct | 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 60.2 tok/s | Runs welltight fit |
| Unlimited OCR (3B-A0.6B) | 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 48.3 tok/s | Runs great | 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 160 tok/s | Runs great |
| EXAONE 4.0 1.2B | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 39.6 tok/s | Runs great | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 88.0 tok/s | Runs great |
| MiniCPM-OCR 1.0 1.3B | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 tok/s | Runs great | 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 86.6 tok/s | Runs great |
| Mixtral 8x7B Instruct | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Slowheavy RAM offload |
| Jamba2 3B | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 16.7 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 80.7 tok/s | Runs great |
| SmolLM3 3B | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 16.4 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 79.4 tok/s | Runs great |
| Qwen2 57B-A14B Instruct | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 tok/s | Slowheavy RAM offload |
| Phi-4 Mini (3.8B) | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 13.2 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 63.6 tok/s | Runs great |
| Mistral Nemo 12B Instruct | 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 64.6 tok/s | Runs welltight fit |
| Ministral 3 3B | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 13.2 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 63.5 tok/s | Runs great |
| Qwen3 4B Thinking 2507 | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 12.6 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 60.8 tok/s | Runs great |
| Gemma 3 4B IT | 42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 11.8 tok/s | Runs well | 45Fair quality (C) · 45 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 56.8 tok/s | Runs great |
| Gemma 3n E2B | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 25.3 tok/s | Runs well | 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 167 tok/s | Runs great |
| Gemma 3 27B IT | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow | 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| InternLM3 8B Instruct | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 tok/s | Slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 54.6 tok/s | Runs great |
| Gemma 2 9B IT | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 5.5 tok/s | Slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 67.2 tok/s | Runs welltight fit |
| DeepCoder 14B Preview | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| MedGemma 4B IT | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 11.8 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 56.8 tok/s | Runs great |
| Qwen3-VL 2B Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 23.8 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs great |
| Devstral Small 1.1 (24B) | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Magistral Small 2507 | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Llama 3.1 Nemotron Nano 4B v1.1 | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 73.9 tok/s | Runs great |
| MedGemma 27B Text IT | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slowheavy RAM offload |
| Phi-3.5 MoE (42B-A6.6B) | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 tok/s | Slowheavy RAM offload |
| Pixtral 12B (2409) | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 63.6 tok/s | Runs welltight fit |
| Qwen3 8B | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 58.6 tok/s | Runs welltight fit |
| Qwen3.5 0.8B | 25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 40.4 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 129 tok/s | Runs great |
| Aya 23 35B | 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek R1 Distill Qwen 14B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welloffloads to RAM |
| JanusCoder 14B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 44.3 tok/s | Runs welloffloads to RAM |
| Magistral Small 2506 | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Granite 4.0 Micro (3B) | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 14.9 tok/s | Runs well | 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 71.9 tok/s | Runs great |
| Mistral Small 3.2 24B | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Hunyuan 4B Instruct | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 12.0 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 57.9 tok/s | Runs great |
| Qwen2.5-Math 72B Instruct | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow | 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| TeleOCR | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 35.7 tok/s | Runs great | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 79.3 tok/s | Runs great |
| GLM-4 9B Chat (2024) | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slow | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 51.1 tok/s | Runs welltight fit |
| GLM-4 9B Chat 1M | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 5.3 tok/s | Slow | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 50.6 tok/s | Runs welltight fit |
| LFM2 1.2B | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 43.3 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 96.3 tok/s | Runs great |
| Yi 1.5 34B Chat | 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Phi-3.5 Mini Instruct | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 13.3 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 126 tok/s | Runs great |
| MiMo-VL 7B RL | 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 10.0 tok/s | Runs well | 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 57.8 tok/s | Runs welltight fit |
| Granite 4.0 H 1B | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Runs great | 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 77.2 tok/s | Runs great |
| Hemmingway 1.5 | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 4.5 tok/s | Slowheavy RAM offload |
| GLM-Z1 9B (0414) | 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 51.1 tok/s | Runs welltight fit |
| Granite 4.0 H Micro | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 15.9 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 76.6 tok/s | Runs great |
| Mistral Small 3.1 24B | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Apertus v1.5 8B | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 5.7 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 53.9 tok/s | Runs welltight fit |
| MiMo 7B RL | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 10.6 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 50.7 tok/s | Runs welltight fit |
| Falcon 180B Chat | 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| InternVL3 8B | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 42.0 tok/s | Runs welltight fit |
| OLMoE 1B-7B Instruct | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 34.4 tok/s | Runs great | 25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 148 tok/s | Runs great |
| Qwen2.5-Omni 7B | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 57.8 tok/s | Runs great |
| LFM2 2.6B | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 43.8 tok/s | Runs great |
| Mistral Small 3 24B (2501) | 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 tok/s | Slowheavy RAM offload |
| AFM 4.5B | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Runs well | 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs great |
| Falcon-H1 3B Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 16.1 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 77.6 tok/s | Runs great |
| Phi-4 Multimodal Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 11.8 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 59.8 tok/s | Runs great |
| Qwen3 1.7B | 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 tok/s | Runs great | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 55.5 tok/s | Runs great |
| Falcon-H1 1.5B Instruct | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 42.2 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 72.7 tok/s | Runs great |
| Llama 3.1 Nemotron Nano 8B v1 | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Aya Vision 8B | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 5.9 tok/s | Slow | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 55.6 tok/s | Runs great |
| Phi-3.5 Vision Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 12.2 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 116 tok/s | Runs great |
| MiniCPM3 4B | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 12.4 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 60.1 tok/s | Runs great |
| MiniCPM4 8B | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 58.6 tok/s | Runs great |
| Reka Flash 3.1 (21B) | 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 15.5 tok/s | Runs welloffloads to RAM |
| Phi-3 Medium 128K Instruct | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 46.0 tok/s | Runs welloffloads to RAM |
| Phi-3 Medium (14B) | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 56.5 tok/s | Runs welltight fit |
| Llama 3.2 3B Instruct | 33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well | 35Basic quality (D) · 35 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 76.1 tok/s | Runs great |
| Dolphin Mistral 24B Venice Edition | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slowheavy RAM offload |
| Hunyuan 7B Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 11.1 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 64.0 tok/s | Runs great |
| Voxtral Small 24B | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | Slowheavy RAM offload |
| Llama 3.2 1B Instruct | 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 40.8 tok/s | Runs great | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 90.8 tok/s | Runs great |
| Qwen2.5 7B Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| Qianfan-OCR 4B | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 70.3 tok/s | Runs great |
| Phi-3 Mini 128K Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 13.3 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 126 tok/s | Runs great |
| Gemma 2 27B IT | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow | 60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Qwen2.5 3B Instruct | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 16.4 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 79.1 tok/s | Runs great |
| Phi-3 Mini 4K Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 13.3 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 64.0 tok/s | Runs great |
| Qwen2.5 1.5B Instruct | 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 42.5 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 tok/s | Runs great |
| LFM2-VL 1.6B | 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 41.4 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 71.3 tok/s | Runs great |
| Mistral-NeMo-Minitron 8B Instruct | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 6.0 tok/s | Slow | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 57.1 tok/s | Runs welltight fit |
| Qwen2.5-VL 7B Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.0 tok/s | Runs well | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 57.9 tok/s | Runs great |
| Solar Pro Preview 22B | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.7 tok/s | Slowheavy RAM offload |
| Olmo 3 7B Instruct | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs welltight fit |
| OLMo 2 13B Instruct | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 9.3 tok/s | Slowheavy RAM offload |
| Dolphin 3.0 R1 Mistral 24B | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 tok/s | Slowheavy RAM offload |
| Granite 3.1 3B-A800M Instruct | 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs great | 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 141 tok/s | Runs great |
| EXAONE 3.5 2.4B | 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 27.2 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 46.7 tok/s | Runs great |
| S5 nano | 35Basic quality (D) · 35 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 37Basic quality (D) · 37 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 52.4 tok/s | Runs great |
| Gemma 3 1B | 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 41.8 tok/s | Runs great | 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 113 tok/s | Runs great |
| Falcon-H1 7B Instruct | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 52.3 tok/s | Runs great |
| InternLM2.5 20B Chat | 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 tok/s | Slowheavy RAM offload |
| Qwen2.5 7B Instruct 1M | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| GLiDE 9B | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 60.5 tok/s | Runs great |
| Foundation-Sec 1.1 8B Instruct | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| LightOnOCR-3 4B | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 11.2 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 53.8 tok/s | Runs great |
| InternVL2.5 8B | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 49.1 tok/s | Runs welltight fit |
| Granite 3.2 2B Instruct | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 20.0 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great |
| Granite 3.3 2B | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 20.0 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great |
| Llama 3.2 11B Vision Instruct | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 58.2 tok/s | Runs welltight fit |
| Qwen1.5 32B Chat | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 4.4 tok/s | Slowheavy RAM offload |
| Phi-4 Mini Reasoning (3.8B) | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 13.2 tok/s | Runs well | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 63.6 tok/s | Runs great |
| LLaVA 1.6 34B | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Voxtral Mini 3B | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.8 tok/s | Runs well | 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 71.2 tok/s | Runs great |
| Qwen2.5-VL 3B Instruct | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 13.5 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 65.2 tok/s | Runs great |
| Hermes 3 Llama 3.2 3B | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 76.1 tok/s | Runs great |
| Phi-3 Vision 128K Instruct | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 12.2 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 116 tok/s | Runs great |
| LFM2 700M | 17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 47.5 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 152 tok/s | Runs great |
| Granite 3.0 3B-A800M Instruct | 17Basic quality (D) · 17 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 141 tok/s | Runs great |
| Hermes 3 (Llama 3.1 8B) | 33Basic quality (D) · 33 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Llama 3.1 8B Instruct | 33Basic quality (D) · 33 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| MiniCPM-V 2.6 8B | 33Basic quality (D) · 33 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 59.3 tok/s | Runs great |
| Granite 3.1 2B Instruct | 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 tok/s | Runs well | 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great |
| Hunyuan 1.8B Instruct | 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 36.6 tok/s | Runs great | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 62.9 tok/s | Runs great |
| Magistral Small 1.2 (24B) | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Nous Hermes 2 SOLAR 10.7B | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow | 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 57.8 tok/s | Runs welltight fit |
| SOLAR 10.7B Instruct | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow | 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 57.8 tok/s | Runs welltight fit |
| Falcon 3 7B Instruct | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 11.1 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 64.4 tok/s | Runs great |
| WeVisOne VL 2B | 22Basic quality (D) · 22 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 26.8 tok/s | Runs well | 27Basic quality (D) · 27 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 100 tok/s | Runs great |
| Gemma 2 2B | 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 25.1 tok/s | Runs well | 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 43.2 tok/s | Runs great |
| EXAONE 3.5 7.8B | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.6 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 50.7 tok/s | Runs welltight fit |
| SmolLM2 1.7B Instruct | 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 38.3 tok/s | Runs great | 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 65.9 tok/s | Runs great |
| Falcon 3 3B Instruct | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 15.7 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 75.7 tok/s | Runs great |
| Ministral 8B (2410) | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.5 tok/s | Runs welltight fit |
| DeepHermes 3 Llama 3 8B Preview | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Dolphin 3.0 Llama 3.1 8B | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Tülu 3 8B | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| DeepSeek LLM 67B Chat | 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek R1 0528 Qwen3 8B | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 58.6 tok/s | Runs welltight fit |
| Granite 3.2 8B Instruct | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs welltight fit |
| Granite 3.3 8B | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs welltight fit |
| Qwen2-VL 2B Instruct | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 37.6 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 51.0 tok/s | Runs great |
| Mistral Small 22B (2409) | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slowheavy RAM offload |
| WeVisOne-VL 4B | 42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 69.0 tok/s | Runs great |
| SmolVLM2 2.2B Instruct | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 37.0 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 109 tok/s | Runs great |
| Phi-3 Small 8K Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 65.0 tok/s | Runs great |
| Qwen2 7B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| Granite 3.0 2B Instruct | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 24.9 tok/s | Runs well | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 42.8 tok/s | Runs great |
| Dolphin 2.9.4 Llama 3.1 8B | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Hermes 2 Pro Llama 3 8B | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| OpenChat 3.6 8B | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| InternVL2 8B | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 49.1 tok/s | Runs welltight fit |
| Command R7B | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 59.8 tok/s | Runs great |
| Granite 3.1 8B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs welltight fit |
| Yi 34B Chat | 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Chandra OCR 2 | 40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 62.9 tok/s | Runs great |
| Qwen2-VL 7B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 10.0 tok/s | Runs well | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 57.9 tok/s | Runs great |
| SmolVLM 2.2B Instruct | 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 37.0 tok/s | Runs great | 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 109 tok/s | Runs great |
| DeepSeek MoE 16B Chat | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 17.0 tok/s | Runs well | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 76.2 tok/s | Runs welloffloads to RAM |
| Yi 1.5 9B Chat | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 5.7 tok/s | Slow | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 54.4 tok/s | Runs great |
| Falcon-H1 0.5B Instruct | 14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 49.6 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 217 tok/s | Runs great |
| LFM2.5 350M | 14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 73.6 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 322 tok/s | Runs great |
| Qwen3 0.6B | 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 46.8 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 150 tok/s | Runs great |
| Qwen2 1.5B Instruct | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 42.5 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 tok/s | Runs great |
| Llama 3 8B Instruct | 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Granite Vision 3.2 2B | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 22.0 tok/s | Runs well | 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 82.0 tok/s | Runs great |
| Command R7B Arabic | 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 59.8 tok/s | Runs great |
| Seed-Coder 8B Reasoning | 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 48.1 tok/s | Runs welltight fit |
| Falcon 3 1B Instruct | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 39.2 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 67.4 tok/s | Runs great |
| InternLM2.5 1.8B Chat | 15Basic quality (D) · 15 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 34.6 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 59.6 tok/s | Runs great |
| Devstral Small 2505 | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload |
| Spark X2.6 1.7B | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 38.3 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 65.9 tok/s | Runs great |
| Qwen1.5 MoE A2.7B Chat | 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 22.5 tok/s | Runs well | 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 80.0 tok/s | Runs welloffloads to RAM |
| InternLM2 Chat 20B | 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 tok/s | Slowheavy RAM offload |
| Falcon-H1R 7B | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 52.3 tok/s | Runs great |
| EXAONE Deep 7.8B | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.6 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 50.7 tok/s | Runs welltight fit |
| InternLM2.5 7B Chat | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 62.0 tok/s | Runs great |
| Llama 2 70B Chat | 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| SenseNova 6.8 Code2Video | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.4 tok/s | Slowheavy RAM offload |
| GLiDE 2B | 14Basic quality (D) · 14 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 34.8 tok/s | Runs great | 17Basic quality (D) · 17 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 59.9 tok/s | Runs great |
| CodeGeeX4 All 9B | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 51.1 tok/s | Runs welltight fit |
| Aya Expanse 8B | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Apertus 8B Instruct | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 49.3 tok/s | Runs welltight fit |
| LFM2-VL 450M | 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 57.3 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 250 tok/s | Runs great |
| LFM2 350M | 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 73.6 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 322 tok/s | Runs great |
| Granite 4.0 H 350M | 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 75.8 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 331 tok/s | Runs great |
| Seed-Coder 8B Instruct | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Runs well | 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 48.1 tok/s | Runs welltight fit |
| Granite 3.0 8B Instruct | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs great |
| OLMo 2 1B Instruct | 11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 76.1 tok/s | Runs great |
| Qwen2.5 Coder 7B Instruct | 38Basic quality (D) · 38 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 52Fair quality (C) · 52 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| RecurrentGemma 9B IT | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.3 tok/s | Slow | 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 41.2 tok/s | Runs welltight fit |
| Zamba2 2.7B Instruct | 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 31.3 tok/s | Runs great | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 42.3 tok/s | Runs great |
| Olmo 3 7B Think | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs welltight fit |
| Mistral 7B Instruct v0.3 | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 66.2 tok/s | Runs great |
| Falcon3 Mamba 7B Instruct | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 54.6 tok/s | Runs great |
| Zamba2 7B Instruct | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 65.2 tok/s | Runs great |
| Qwen2.5 Coder 3B Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 16.4 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 79.1 tok/s | Runs great |
| SmolLM 1.7B Instruct | 11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 38.3 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 65.9 tok/s | Runs great |
| OpenReasoning Nemotron 7B | 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| GLiDE 0.8B | 10Basic quality (D) · 10 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 46.8 tok/s | Runs great | 11Basic quality (D) · 11 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 150 tok/s | Runs great |
| EXAONE 3.0 7.8B Instruct | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 10.6 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 61.4 tok/s | Runs great |
| Qwen2.5 Coder 1.5B Instruct | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 42.5 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 tok/s | Runs great |
| Dolphin 2.9 Llama 3 8B | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Qwen1.5 14B Chat | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Codestral 22B | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slowheavy RAM offload |
| Qwen2.5-Omni 3B | 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.8 tok/s | Runs well | 29Basic quality (D) · 29 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 60.1 tok/s | Runs great |
| OLMo 2 7B Instruct | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 65.8 tok/s | Runs welltight fit |
| Hermes 2 Pro Mistral 7B | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Starling LM 7B Beta | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| SmolVLM 500M Instruct | 10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 50.5 tok/s | Runs great | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 221 tok/s | Runs great |
| Qwen2.5 0.5B Instruct | 10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 52.6 tok/s | Runs great | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 230 tok/s | Runs great |
| LFM2.5 230M | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 51.6 tok/s | Runs great | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 490 tok/s | Runs great |
| CogVLM2 Llama 3 Chat 19B | 31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow | 31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 7.1 tok/s | Slowheavy RAM offload |
| DeepScaleR 1.5B Preview | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 36.8 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 63.3 tok/s | Runs great |
| OpenChat 3.5 (0106) | 24Basic quality (D) · 24 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Foundation-Sec 8B Reasoning | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Code Llama 70B Instruct | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mistral 7B Instruct v0.2 | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Nous Hermes 2 Mistral 7B DPO | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| OpenChat 3.5 (1210) | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| StableLM 2 1.6B Chat | 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 39.9 tok/s | Runs great | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 68.7 tok/s | Runs great |
| StableLM 2 Zephyr 1.6B | 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 39.9 tok/s | Runs great | 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 68.7 tok/s | Runs great |
| Hunyuan 0.5B Instruct | 8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 47.7 tok/s | Runs great | 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 209 tok/s | Runs great |
| SmolLM2 360M Instruct | 8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 71.6 tok/s | Runs great | 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 313 tok/s | Runs great |
| DeepSeek R1 Distill Llama 8B | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Aya 23 8B | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 tok/s | Runs welltight fit |
| Yi 1.5 6B Chat | 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 10.8 tok/s | Runs well | 27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 55.0 tok/s | Runs great |
| DeepSeek Coder 33B Instruct | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 tok/s | Very slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 tok/s | Slowheavy RAM offload |
| Fara 7B | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 10.0 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 57.9 tok/s | Runs great |
| LLM4Decompile 22B V2 | 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow | 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slowheavy RAM offload |
| OpenHermes 2.5 Mistral 7B | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Starling LM 7B Alpha | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Gemma 1.1 7B IT | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 5.9 tok/s | Slow | 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Runs welloffloads to RAM |
| Phi-2 2.7B | 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 29.9 tok/s | Runs well | 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 87.9 tok/s | Runs great |
| StableLM Zephyr 3B | 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 29.7 tok/s | Runs well | 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 87.3 tok/s | Runs great |
| Yi Coder 9B Chat | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.7 tok/s | Slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 54.4 tok/s | Runs welltight fit |
| Nemotron Mini 4B Instruct | 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 15.6 tok/s | Runs well | 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 1.5B | 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 36.8 tok/s | Runs great | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 63.3 tok/s | Runs great |
| SmolVLM 256M Instruct | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 45.7 tok/s | Runs great | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 433 tok/s | Runs great |
| Qwen2 0.5B Instruct | 6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 52.6 tok/s | Runs great | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 230 tok/s | Runs great |
| Gemma 3 270M | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 44.0 tok/s | Runs great | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 417 tok/s | Runs great |
| ERNIE 4.5 0.3B | 6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 71.6 tok/s | Runs great | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 313 tok/s | Runs great |
| Mistral 7B Instruct v0.1 | 21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Falcon Mamba 7B Instruct | 21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 54.6 tok/s | Runs great |
| Qwen2.5-Math 1.5B Instruct | 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 42.5 tok/s | Runs great | 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 tok/s | Runs great |
| TinyLlama 1.1B Chat | 5Basic quality (D) · 5 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 46.0 tok/s | Runs great | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 102 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 7B | 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 63.0 tok/s | Runs great |
| Gemma 2B IT | 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 33.1 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 44.9 tok/s | Runs great |
| Gemma 7B IT | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.9 tok/s | Slow | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Runs welloffloads to RAM |
| SmolLM 360M Instruct | 5Basic quality (D) · 5 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 71.6 tok/s | Runs great | 5Basic quality (D) · 5 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 313 tok/s | Runs great |
| LLM4Decompile 9B V2 | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.7 tok/s | Slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 54.4 tok/s | Runs welltight fit |
| StableLM 2 12B Chat | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 tok/s | Slow | 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 51.1 tok/s | Runs welltight fit |
| Orca 2 13B | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 24.6 tok/s | Slowheavy RAM offload |
| Neural Chat 7B v3.3 | 19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| LLaVA 1.6 Mistral 7B | 19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Runs well | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 63.4 tok/s | Runs great |
| d1 2B | 17Basic quality (D) · 17 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 34.1 tok/s | Runs great | 21Basic quality (D) · 21 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 58.7 tok/s | Runs great |
| StarCoder2 15B Instruct | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 47.4 tok/s | Runs welloffloads to RAM |
| SmolLM2 135M Instruct | 4Basic quality (D) · 4 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 91.4 tok/s | Runs great | 4Basic quality (D) · 4 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 866 tok/s | Runs great |
| surya ocr 2.5 | 14Basic quality (D) · 14 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 50.9 tok/s | Runs great | 15Basic quality (D) · 15 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 163 tok/s | Runs great |
| Granite Code 34B Instruct | 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowheavy RAM offload |
| Zephyr 7B Beta | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Falcon-H1 Tiny 90M Instruct | 3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 132 tok/s | Runs great | 3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 1,252 tok/s | Runs great |
| Llama 2 13B Chat | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 24.6 tok/s | Slowheavy RAM offload |
| Qwen1.5 7B Chat | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 10.8 tok/s | Runs well | 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 33.7 tok/s | Runs welloffloads to RAM |
| Baichuan 2 13B Chat | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 21.2 tok/s | Slowheavy RAM offload |
| Yi Coder 1.5B Chat | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 76.1 tok/s | Runs great |
| DeepSeek Prover V2 7B | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 12.0 tok/s | Runs well | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 114 tok/s | Runs welltight fit |
| SmolLM 135M Instruct | 2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 91.4 tok/s | Runs great | 2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 866 tok/s | Runs great |
| Code Llama 34B Instruct | 37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 tok/s | Very slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| CodeGemma 7B | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 5.9 tok/s | Slow | 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Runs welloffloads to RAM |
| Yi 6B Chat | 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 10.8 tok/s | Runs well | 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 55.0 tok/s | Runs great |
| Orca 2 7B | 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs welltight fit |
| InternLM2 Math Plus 20B | 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 tok/s | Slowheavy RAM offload |
| Llama 2 7B Chat | 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 58.8 tok/s | Runs welltight fit |
| DeepSeek Coder 1.3B Instruct | 11Basic quality (D) · 11 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 37.5 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 83.4 tok/s | Runs great |
| LLM4Decompile 1.3B V2 | 11Basic quality (D) · 11 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 37.5 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 83.4 tok/s | Runs great |
| WizardLM 13B v1.2 | 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 24.6 tok/s | Slowheavy RAM offload |
| LLaVA 1.5 13B | 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 23.2 tok/s | Slowheavy RAM offload |
| Codestral Mamba 7B | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 54.4 tok/s | Runs great |
| Baichuan 2 7B Chat | 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 11.1 tok/s | Runs well | 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 63.9 tok/s | Runs welltight fit |
| Stable Code Instruct 3B | 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 29.7 tok/s | Runs well | 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 87.3 tok/s | Runs great |
| DeepSeek Coder 6.7B Instruct | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs welltight fit |
| Qwen2.5-Math 7B Instruct | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 52.0 tok/s | Runs great |
| DeepSeek LLM 7B Chat | 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 12.0 tok/s | Runs well | 17Basic quality (D) · 17 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 57.4 tok/s | Runs welltight fit |
| Mathstral 7B | 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 66.2 tok/s | Runs great |
| Vicuna 13B v1.5 | 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 24.6 tok/s | Slowheavy RAM offload |
| LLM4Decompile 6.7B V2 | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs welltight fit |
| Qwen2.5 Coder 0.5B Instruct | 8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 52.6 tok/s | Runs great | 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 230 tok/s | Runs great |
| LLaVA 1.5 7B | 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 11.8 tok/s | Runs well | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 87.9 tok/s | Runs great |
| StarCoder2 15B (base) | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 47.4 tok/s | Runs welloffloads to RAM |
| Granite Code 20B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 22.4 tok/s | Runs welloffloads to RAM |
| Code Llama 13B Instruct | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 tok/s | Slow | 21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 2/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| StarCoder2 3B | 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 27.4 tok/s | Runs well | 18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 80.7 tok/s | Runs great |
| SQLCoder 7B v2 | 21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs welltight fit |
| CodeGemma 2B | 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 33.1 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 44.9 tok/s | Runs great |
| Granite Code 3B Instruct (128K) | 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 23.9 tok/s | Runs well | 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 95.7 tok/s | Runs great |
| InternLM2 Math Plus 7B | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 tok/s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 62.0 tok/s | Runs great |
| Vicuna 7B v1.5 | 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 92.1 tok/s | Runs great |
| Granite Code 8B Instruct (128K) | 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well | 31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 49.3 tok/s | Runs welltight fit |
| OLMo 7B Instruct | 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 tok/s | Runs well | 13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 69.7 tok/s | Runs great |
| InternLM 7B | 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 11.4 tok/s | Runs well | 11Basic quality (D) · 11 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 65.6 tok/s | Runs great |
| WizardMath 7B v1.1 | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 66.3 tok/s | Runs great |
| Code Llama 7B Instruct | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs welltight fit |
| StarCoder 15B | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 49.8 tok/s | Runs welltight fit |
| StarCoder2 7B | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 11.6 tok/s | Runs well | 23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 55.3 tok/s | Runs great |
| Falcon 40B Instruct | 15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow | 13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 34/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slowheavy RAM offload |
| Falcon 7B Instruct | 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well | 5Basic quality (D) · 5 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 54.9 tok/s | Runs great |
| Kimi K3.1 Pro (2.8T) | 69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen3.8 Max (2.4T-A95B) | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kimi K3 (2.8T) | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4 Pro (1.6T-A49B) | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DeepSeek V4 Pro (April 2026) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
Image models
60 of 60 image models run on the Intel Xeon D-2700 series NAS (512 GB). 471 GB usable for models.
49 of 60 image models run on the Intel Arc A580. 8.0 GB usable for models.
| Model | QualityXeon D-2700 series NAS | SpeedXeon D-2700 series NAS | RunsXeon D-2700 series NAS | QualityArc A580 | SpeedArc A580 | RunsArc A580 |
|---|---|---|---|---|---|---|
| HunyuanImage 3.0 (80B-A13B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 min | Very slow | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Cosmos3-Super Text2Image (64B) | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 48.2 min | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| FLUX.2 [dev] | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 min | Very slow | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Krea 2 Turbo | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 min | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 22 s | Runs welltight fit · CPU offload |
| Qwen-Image 2.1 | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 min | Very slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ideogram 4 | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 30.1 min | Very slow | 85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 2.7 min | Very slowCPU offload |
| Fibo 2.0 Dev | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 27.1 min | Very slow | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| FLUX 3 Image Klein | 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 6.9 min | Very slow | 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 32 s | Runs wellencoder in RAM |
| Qwen-Image 2512 | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 h | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Qwen-Image 2.1 Turbo | 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 14.0 min | Very slow | 82Great quality (A) · 82 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| FLUX.2 [klein] 9B | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 2.2 min | Slow | 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 9.4 s | Runs greatCPU offload |
| Qwen-Image | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 h | Very slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Ming-Image 0.1 Design | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 19.7 min | Very slow | 84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| FireRed-Image-Edit 1.1 | 87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 h | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| ERNIE-Image Turbo | 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 min | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs welltight fit · encoder in RAM |
| ERNIE-Image | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 26.5 min | Very slow | 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 min | Slowtight fit · encoder in RAM |
| Z-Image Turbo | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 min | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 14 s | Runs wellencoder in RAM |
| Qwen-Image-Edit 2511 | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 h | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| HiDream-I1 Full | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 min | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at NF4, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 4.8 min | Very slowCPU offload |
| FLUX.2 [klein] 4B | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 72 s | Slow | 77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 s | Runs greatencoder in RAM |
| HiDream-I1 Dev | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 min | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 min | SlowCPU offload |
| FLUX.1 Krea [dev] | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 14.5 min | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 63 s | Slowtight fit · CPU offload |
| FLUX.1 Kontext [dev] | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 26.5 min | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 1.9 min | Slowtight fit · CPU offload |
| MOSS-Image SFT | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 16.9 min | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 59 s | Slowtight fit · encoder in RAM |
| FLUX.1 [dev] | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 14.5 min | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 63 s | Slowtight fit · CPU offload |
| Z-Image | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 min | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 min | Slowencoder in RAM |
| HiDream-I1 Fast | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 min | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at NF4, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 64 s | SlowCPU offload |
| Chroma1-HD | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 min | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at NF4, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 min | Slowtight fit · encoder in RAM |
| FLUX.1 Fill [dev] | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 15.1 min | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 65 s | Slowtight fit · CPU offload |
| FLUX.1 [schnell] | 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 2.2 min | Slow | 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 10 s | Runs welltight fit · CPU offload |
| Iris-3B | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 19.3 min | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 1.5 min | SlowCPU offload |
| CogView4 6B | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 21.7 min | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 min | SlowCPU offload |
| Stable Diffusion 3.5 Large Turbo | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 1.9 min | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 9.0 s | Runs welltight fit · encoder in RAM |
| Stable Diffusion 3.5 Large | 66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 13.3 min | Very slow | 61Good quality (B) · 61 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 62 s | Slowtight fit · encoder in RAM |
| SDXL Turbo | 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 9.8 s | Runs great | 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 0.6 s | Runs great |
| OmniGen2 | 66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 19.3 min | Very slow | 64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 68 s | Slowencoder in RAM |
| DreamShaper XL v2 Turbo | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 min | Slow | 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 s | Runs great |
| SDXL-Lightning (4-step) | 54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 51 s | Slow | 52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.8 s | Runs great |
| Juggernaut XL v9 | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 min | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well |
| RealVisXL V5.0 | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 min | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well |
| Kolors | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.8 min | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 17 s | Runs wellencoder in RAM |
| Lumina-Image 2.0 | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 8.4 min | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 28 s | Runs welltight fit |
| Animagine XL 4.0 | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.1 min | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 17 s | Runs well |
| Illustrious XL v0.1 | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.1 min | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 17 s | Runs well |
| Playground v2.5 | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 9.0 min | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 30 s | Runs well |
| Pony Diffusion V6 XL | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 4.6 min | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 15 s | Runs well |
| Stable Diffusion 3.5 Medium | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 7.2 min | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 25 s | Runs wellencoder in RAM |
| AuraFlow v0.3 | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 16.9 min | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 75 s | Slowtight fit |
| Animagine XL 3.1 | 56Good quality (B) · 56 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 5.1 min | Very slow | 54Fair quality (C) · 54 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 17 s | Runs well |
| Stable Diffusion XL 1.0 | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 min | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well |
| SD Turbo | 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 s | Runs great | 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 s | Runs great |
| PixArt-Σ XL 1024 | 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 min | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 7.0 s | Runs greatencoder in RAM |
| Stable Diffusion 3 Medium | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 min | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 13 s | Runs greatencoder in RAM |
| Stable Cascade | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 6.0 min | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 21 s | Runs welltight fit · encoder in RAM |
| Hunyuan-DiT v1.2 | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 7.2 min | Very slow | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 28 s | Runs wellencoder in RAM |
| LCM DreamShaper v7 | 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well | 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 s | Runs great |
| Kandinsky 3 | 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 10.9 min | Very slow | 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 52 s | SlowCPU offload |
| Realistic Vision V5.1 | 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 87 s | Slow | 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 s | Runs great |
| DreamShaper 8 | 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 87 s | Slow | 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 s | Runs great |
| Stable Diffusion 1.5 | 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 87 s | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 s | Runs great |
Video models
43 of 43 video models run on the Intel Xeon D-2700 series NAS (512 GB). 471 GB usable for models.
7 of 43 video models run on the Intel Arc A580. 8.0 GB usable for models.
| Model | QualityXeon D-2700 series NAS | SpeedXeon D-2700 series NAS | RunsXeon D-2700 series NAS | QualityArc A580 | SpeedArc A580 | RunsArc A580 |
|---|---|---|---|---|---|---|
| Cosmos3-Super Image2Video (64B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 45.2 h | Very slow | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| MiniMax H3 (33B, video + audio) | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 20.9 h | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LTX-2.5 (22B, video + audio) | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 h | Very slow | 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kandinsky 6.0 Pro (29B, video + audio) | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 59.1 h | Very slow | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LTX-2.3 | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 8.0 h | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.2 I2V A14B | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 h | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.2 T2V A14B | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 h | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LTX-2 (19B, video + audio) | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 8.0 h | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Bernini-R A14B (video generation + editing) | 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 14.5 h | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| HunyuanVideo 1.5 (8.3B) | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 36.2 h | Very slow | 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| SCAIL-2 14B (character animation) | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 h | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.2 Animate 14B | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 38.2 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.1 VACE 14B | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| SkyReels V2 T2V 14B 720P | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 48.2 h | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.1 I2V 14B 720P | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 40.2 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.1 T2V 14B | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 40.2 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Step-Video T2V (30B) | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 62.3 h | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan-Dancer 14B (music to dance) | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 88.4 h | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.2 S2V 14B (speech to video) | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 20.1 h | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| HY-OmniWeaving (8.3B, unified video) | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 h | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| FramePack I2V (HunyuanVideo 13B) | 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 8.0 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.1 I2V 14B 480P | 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 18.1 h | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| SkyReels V2 T2V 14B 540P | 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 28.1 h | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| HunyuanVideo 13B | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 48.2 h | Very slow | 66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| HunyuanVideo I2V 13B | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 48.2 h | Very slow | 66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LTX-Video 13B 0.9.8 (distilled) | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 min | Very slow | 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Cosmos-Predict2 14B Video2World | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 h | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Wan 2.2 TI2V 5B | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 h | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Open-Sora 2.0 (11B) | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 60.3 h | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Kandinsky 6.0 Video Lite (3B, video + audio) | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 6.2 h | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Mochi 1 Preview (10B) | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 22.1 h | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Cosmos 1.0 Diffusion 7B Text2World | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 11.1 h | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| CogVideoX 1.5 5B | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 18.1 h | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Cosmos-Predict2 2B Video2World | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 h | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| LTX-Video 2B | 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 30.1 min | Slow | 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 min | Runs greatencoder in RAM |
| CogVideoX 5B I2V | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 h | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 15.7 min | SlowCPU offload |
| CogVideoX 5B | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 h | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 15.7 min | SlowCPU offload |
| Wan 2.1 VACE 1.3B | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 h | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 22.6 min | SlowCPU offload |
| Wan 2.1 T2V 1.3B | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.8 h | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 16.9 min | Slowtight fit · encoder in RAM |
| Allegro (2.8B) | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 h | Very slow | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| SkyReels V2 Diffusion Forcing 1.3B | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 6.0 h | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| CogVideoX 2B | 45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 min | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 min | Runs wellencoder in RAM |
| AnimateDiff v3 (SD 1.5) | 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 min | Slow | 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 89 s | Runs great |
Decision models
70 of 70 decision models run on the Intel Xeon D-2700 series NAS (512 GB). 471 GB usable for models.
65 of 70 decision models run on the Intel Arc A580. 8.0 GB usable for models.
| Model | QualityXeon D-2700 series NAS | SpeedXeon D-2700 series NAS | RunsXeon D-2700 series NAS | QualityArc A580 | SpeedArc A580 | RunsArc A580 |
|---|---|---|---|---|---|---|
| OpenAI Privacy Filter | 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 50 ms | Runs great | 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 ms | Runs great |
| Llama Prompt Guard 2 22M | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 118 ms | Runs great | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 7.4 ms | Runs great |
| Jina Reranker v3.5 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 910 ms | Slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 32 ms | Runs great |
| GLiNER2.5 Decide | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 396 ms | Runs well | 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 16 ms | Runs great |
| Jina Reranker v3 | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 910 ms | Slow | 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 32 ms | Runs great |
| Qwen3 Reranker 4B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 6.1 s | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 173 ms | Runs well |
| Qwen3 Reranker 8B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 12.4 s | Very slow | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 331 ms | Runs well |
| FRIDA-Decisions | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 660 ms | Slow | 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 23 ms | Runs great |
| GLiClass Base v3 | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 156 ms | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 8.5 ms | Runs great |
| GLiClass ModernBERT Large v3 | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 324 ms | Runs well | 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 13 ms | Runs great |
| zerank-2 | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 6.1 s | Very slow | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 173 ms | Runs well |
| Skywork Reward V2 Llama 3.1 8B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 24.0 s | Very slow | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| Llama Prompt Guard 2 86M | 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 452 ms | Slow | 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 17 ms | Runs great |
| DeBERTa v3 Base Zero-shot v2.0 | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 148 ms | Runs well | 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 8.3 ms | Runs great |
| GTE Reranker ModernBERT Base | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 244 ms | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 11 ms | Runs great |
| Qwen3 Reranker 0.6B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 910 ms | Slow | 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 32 ms | Runs great |
| Shieldstral 1.0 3B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 s | Very slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 165 ms | Runs well |
| DeBERTa v3 Large Zero-shot v2.0 | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 356 ms | Runs well | 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 14 ms | Runs great |
| Intern-Decision 4B | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 s | Very slow | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 108 ms | Runs great |
| Granite Embedding Reranker English R2 | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 244 ms | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 11 ms | Runs great |
| GLiNER2 Base v1 | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 172 ms | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 9.0 ms | Runs great |
| mxbai-rerank-large v2 | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 2.3 s | Very slow | 82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 76 ms | Runs great |
| d1 3B | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 2.4 s | Very slow | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 76 ms | Runs great |
| ModernBERT Large Zero-shot v2.0 | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 324 ms | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 13 ms | Runs great |
| GLiDE 27B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 20.9 s | Very slow | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| mxbai-rerank-base v2 | 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 744 ms | Slow | 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 27 ms | Runs great |
| zerank-1 small | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 s | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 84 ms | Runs great |
| Skywork Reward V2 Qwen3 8B | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 24.2 s | Very slow | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLiGuard 300M | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 340 ms | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 14 ms | Runs great |
| Laya | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 340 ms | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 14 ms | Runs great |
| Jina Reranker v2 Base Multilingual | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 452 ms | Slow | 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 17 ms | Runs great |
| LemonDecider 4B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 s | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 97 ms | Runs great |
| ProtectAI DeBERTa v3 Prompt Injection v2 | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 292 ms | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 13 ms | Runs great |
| ms-marco MiniLM L6 v2 | 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 46 ms | Runs great | 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 5.1 ms | Runs great |
| DuoGuard 0.5B | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 788 ms | Slow | 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 27 ms | Runs great |
| BGE Reranker v2 Gemma | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 s | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 109 ms | Runs great |
| BGE Reranker v2 M3 | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 916 ms | Slow | 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 31 ms | Runs great |
| Qwen3Guard Gen 8B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 14.0 s | Very slow | 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 416 ms | Slow |
| Qwen3Guard Gen 4B | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 7.5 s | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 250 ms | Runs well |
| Laya Multilingual | 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 260 ms | Runs well | 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 12 ms | Runs great |
| Llama 3.1 Nemotron Safety Guard 8B v3 | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 13.7 s | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 453 ms | Slowtight fit |
| Granite Guardian 4.1 8B | 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 14.3 s | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 426 ms | Slow |
| HHEM 2.1 Open | 62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 356 ms | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 14 ms | Runs great |
| Skywork Reward V2 Qwen3 0.6B | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 1.9 s | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 61 ms | Runs great |
| GLiNER Multi v2.1 | 62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 236 ms | Runs well | 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11 ms | Runs great |
| Qwen3Guard Gen 0.6B | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 1.3 s | Slow | 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 72 ms | Runs great |
| WildGuard 7B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 12.4 s | Very slow | 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 388 ms | Runs well |
| Granite Guardian 3.3 8B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 13.9 s | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 415 ms | Slow |
| NuExtract 2.0 4B | 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 6.3 s | Very slow | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 345 ms | Runs well |
| BART Large MNLI | 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 332 ms | Runs well | 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 14 ms | Runs great |
| CompassJudger-2 32B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 287.1 s | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 60.9 s | Very slowheavy RAM offload |
| gpt-oss-safeguard 120B | 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 23.1 s | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| NuExtract 2.0 2B | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 s | Very slow | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 156 ms | Runs well |
| LettuceDetect Large | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 1.3 s | Slow | 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 42 ms | Runs great |
| DynaGuard 8B | 79Great quality (A) · 79 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 62.9 s | Very slow | 75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 s | Very slow |
| Nemotron Content Safety Reasoning 4B | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 s | Very slow | 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 2.2 s | Very slow |
| Selene 1 Mini 8B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 70.4 s | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 s | Very slowtight fit |
| ShieldGemma 27B | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 41.1 s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 2.4 s | Very slowheavy RAM offload |
| gpt-oss-safeguard 20B | 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 16.5 s | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 s | Very slowheavy RAM offload |
| ShieldGemma 9B | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 14.0 s | Very slow | 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 373 ms | Runs welltight fit |
| CompassJudger-2 7B | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 66.8 s | Very slow | 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 s | Very slow |
| Llama Guard 3 8B | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 13.7 s | Very slow | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 408 ms | Slow |
| ShieldGemma 2B | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 s | Very slow | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 113 ms | Runs great |
| Llama Guard 4 12B | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 s | Very slow | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 714 ms | Slowoffloads to RAM |
| Prometheus 2 8x7B | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 113.6 s | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| DynaGuard 1.7B | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 15.6 s | Very slow | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 1.1 s | Slow |
| Prometheus 2 7B | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 63.4 s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 s | Very slow |
| Llama Guard 3 1B | 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 s | Very slow | 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 98 ms | Runs great |
| GLIDER | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 33.5 s | Very slow | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 s | Very slow |
| Flow Judge v0.1 | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 33.5 s | Very slow | 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 s | Very slow |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.