Intel Xeon W-2100 series NAS (256 GB) vs Intel Arc B570 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 W-2100 series NAS (256 GB)
For general chat: It runs 116 more LLMs (580 vs 464). On the other hand, the Intel Arc B570 is about 8.5× faster on its own top models.
 Intel Xeon W-2100 series NAS (256 GB)
|
 Intel Arc B570
|
|
|---|---|---|
| Memory | 256 GB unified | 10.0 GB VRAM |
| Usable for models | 230 GB | 10.0 GB |
| Memory bandwidth | 85 GB/s | 380 GB/s |
| FP16 compute | 0.8 TFLOPS | 23.0 TFLOPS |
| Launch price | — | $219 |
| Released | 2017 | 2025 |
| LLMs that run | 580 of 619 | 464 of 619 |
| LLMs that run well | 366 | 384 |
| Image models that run | 60 of 60 | 52 of 60 |
| Video models that run | 43 of 43 | 11 of 43 |
| Decision models that run | 70 of 70 | 66 of 70 |
| Top-10 LLM average score | 90 | 92 |
| Top-10 LLM average speed | 4.8 tok/s | 41.0 tok/s |
| Best LLM | Qwen3.8 Flash Next (125B-A6B) | 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
580 of 619 LLMs run on the Intel Xeon W-2100 series NAS (256 GB). 230 GB usable for models.
464 of 619 LLMs run on the Intel Arc B570. 10.0 GB usable for models.
| Model | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS | QualityArc B570 | SpeedArc B570 | RunsArc B570 |
|---|---|---|---|---|---|---|
| Qwen3.8 Flash Next (125B-A6B) | 91Excellent quality (A+) · 91 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. | 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 |
| 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 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 |
| 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 90/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 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) | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 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 |
| 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 90/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 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 |
| GLM-5.3 Flash (320B-A18B) | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 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 |
| DeepSeek V4 Flash (284B-A13B) | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | 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 |
| 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 89/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 tok/s | 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 |
| 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 89/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | 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 |
| Hunyuan Hy3 (295B-A21B) | 89Excellent quality (A+) · 89 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. | 3.1 tok/s | 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 |
| Nemotron 3.5 Super VL 120B-A12B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 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 |
| 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 88/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 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 |
| 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 87/100 (quality, fit, speed and memory use) sets the ranking. | 4.3 tok/s | 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 |
| Kolibri 1 (78B-A3.5B) | 90Excellent quality (A+) · 90 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. | 12.5 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 |
| Nemotron 3 Super 120B-A12B | 87Excellent quality (A+) · 87 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. | 3.7 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 |
| 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | 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 |
| 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | 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 |
| MiniMax M3.1 Flash (428B-A23B) | 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. | 3.6 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 |
| 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | 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 |
| gpt-oss 120B | 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 13.1 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 |
| Qwen3.6 35B-A3B | 88Excellent quality (A+) · 88 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. | 20.3 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. | 34.7 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 84/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | 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 |
| MiniCPM-V 4.7 35B-A3B | 88Excellent quality (A+) · 88 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. | 20.3 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. | 35.0 tok/s | Slowheavy RAM offload |
| Qwen3.5 35B-A3B | 88Excellent quality (A+) · 88 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. | 20.3 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. | 34.7 tok/s | Slowheavy RAM offload |
| 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 84/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 39.2 tok/s | Slowheavy RAM offload |
| Ling 3.0 Flash (127B-A5B) | 79Great quality (A) · 79 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. | 10.2 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 |
| Qwen3-Next 80B-A3B Thinking | 81Great quality (A) · 81 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. | 20.3 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 |
| K2-Horizon (375B-A23B) | 79Great quality (A) · 79 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. | 3.6 tok/s | 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 |
| MiniMax M3 (427B) | 79Great quality (A) · 79 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. | 3.3 tok/s | 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 |
| Nex N2 Mini (35B-A3B) | 87Excellent quality (A+) · 87 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. | 20.3 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 35.1 tok/s | Slowheavy RAM offload |
| 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 83/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | 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 |
| Sage-A1.5 35B-A3B | 86Excellent quality (A+) · 86 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. | 20.3 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. | 34.7 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 83/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 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 |
| Gemma 4 26B-A4B | 91Excellent quality (A+) · 91 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. | 11.5 tok/s | Runs well | 64Good quality (B) · 64 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. | 74.2 tok/s | Runs welloffloads to RAM |
| Ornith 1.5 35B-A3B | 85Excellent quality (A+) · 85 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. | 20.3 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. | 34.7 tok/s | Slowheavy RAM offload |
| Llama 3.1 Nemotron Ultra 253B v1 | 81Great quality (A) · 81 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. | 0.3 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 |
| Apodex 1.1 Mini (35B-A3B) | 84Great quality (A) · 84 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. | 20.3 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Slowheavy RAM offload |
| Ornith 1.0 35B-A3B | 84Great quality (A) · 84 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. | 20.3 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Slowheavy RAM offload |
| dots.llm1 Instruct | 75Great quality (A) · 75 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. | 3.2 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 |
| GLM-4.6V | 82Great quality (A) · 82 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. | 3.7 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 |
| 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 82/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 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 235B-A22B Instruct 2507 | 75Great quality (A) · 75 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 | 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 |
| 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 82/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 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 |
| GLM-4.7 Flash (30B-A3B) | 83Great quality (A) · 83 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. | 20.3 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 36.4 tok/s | Slowheavy RAM offload |
| Agents-A1 35B-A3B | 82Great quality (A) · 82 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. | 20.3 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 35.1 tok/s | Slowheavy RAM offload |
| Qwen AgentWorld 35B-A3B | 82Great quality (A) · 82 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. | 20.3 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 35.3 tok/s | Slowheavy RAM offload |
| Qwen3-VL 235B-A22B Instruct | 74Great quality (A) · 74 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 | 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 |
| Qwen3 235B-A22B | 73Great quality (A) · 73 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 | 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 |
| K-EXAONE 236B-A23B | 73Great quality (A) · 73 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. | 3.6 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 |
| Mistral Small 4 (119B-A6B) | 76Great quality (A) · 76 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. | 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 |
| Mistral Large 2 (123B) | 78Great quality (A) · 78 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. | 0.3 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 |
| Pixtral Large 124B (2411) | 78Great quality (A) · 78 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. | 0.3 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 |
| GLM-4.5V | 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. | 3.7 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 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 |
| Raon-1 mini Preview (30B-A4B) | 87Excellent quality (A+) · 87 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. | 10.2 tok/s | Runs well | 61Good quality (B) · 61 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. | 61.7 tok/s | Runs welloffloads to RAM |
| ERNIE 4.5 300B-A47B | 76Great quality (A) · 76 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. | 1.4 tok/s | Very slowtight fit | 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 | 79Great quality (A) · 79 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. | 3.7 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 |
| GLM-4.5 Air (106B-A12B) | 77Great quality (A) · 77 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. | 3.7 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 |
| Command A+ (218B-A25B) | 73Great quality (A) · 73 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. | 3.3 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 |
| Baichuan M3 235B-A22B | 70Great quality (A) · 70 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. | 3.8 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 |
| DeepSeek V2.5 1210 | 68Good quality (B) · 68 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. | 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 |
| Devstral 2 (123B) | 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. | 0.3 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 |
| 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 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. | 33.8 tok/s | Slowheavy RAM offload |
| Qwen3 Coder Next (80B-A3B) | 81Great quality (A) · 81 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. | 20.3 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 V2.5 | 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. | 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 |
| GLM-4.7 (355B-A32B) | 65Good quality (B) · 65 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 | 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 |
| 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 4.5 tok/s | 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 |
| NorthCUA Pro | 65Good quality (B) · 65 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. | 4.9 tok/s | Slowtight fit | 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 |
| KAT-Coder V2.5 Dev (35B-A3B) | 86Excellent quality (A+) · 86 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. | 20.3 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. | 35.3 tok/s | Slowheavy RAM offload |
| MiniMax M2.7 (230B-A10B) | 65Good quality (B) · 65 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. | 10.4 tok/s | Runs well | 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 |
| Ling Flash 2.0 (100B-A6B) | 72Great quality (A) · 72 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. | 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 |
| MiniMax M2.5 (230B-A10B) | 64Good quality (B) · 64 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. | 10.4 tok/s | Runs well | 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 |
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 17.6 tok/s | Runs well | 56Good quality (B) · 56 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. | 66.2 tok/s | Runs welloffloads to RAM |
| Qwen3 235B-A22B Thinking 2507 | 76Great quality (A) · 76 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. | 3.8 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 |
| MiniMax M2.1 (230B-A10B) | 63Good quality (B) · 63 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. | 10.4 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 |
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 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. | 42.4 tok/s | Slowheavy RAM offload |
| Ling 3.0 flash Sante | 64Good quality (B) · 64 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. | 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 |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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. | 33.1 tok/s | Slowheavy RAM offload |
| Command A Reasoning (111B) | 82Great quality (A) · 82 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. | 0.3 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 M2 (230B-A10B) | 62Good quality (B) · 62 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. | 10.4 tok/s | Runs well | 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 |
| Groot 65B A6B 261023 | 66Good quality (B) · 66 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. | 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 |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 24.5 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 76.1 tok/s | Runs welloffloads to RAM |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 17.6 tok/s | Runs well | 53Fair quality (C) · 53 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. | 66.2 tok/s | Runs welloffloads to RAM |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 32.9 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | Slowtight fit | 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 |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 15.5 tok/s | Runs well | 54Fair quality (C) · 54 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. | 71.3 tok/s | Runs welloffloads to RAM |
| Hunyuan A13B (80B-A13B) | 73Great quality (A) · 73 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. | 3.4 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 |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 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 |
| Hunyuan Hy-Memory 30B-A3B | 80Great quality (A) · 80 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. | 20.3 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. | 36.3 tok/s | Slowheavy RAM offload |
| DeepSeek Coder V2 (236B) | 70Great quality (A) · 70 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. | 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 |
| GLM-4.6 (355B-A32B) | 58Good quality (B) · 58 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. | 3.3 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 |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 32.9 tok/s | Slowheavy RAM offload |
| Qwen3 30B-A3B | 70Great quality (A) · 70 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. | 18.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 33.1 tok/s | Slowheavy RAM offload |
| DeepSeek V2 Chat | 58Good quality (B) · 58 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. | 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 |
| Sarvam 30B | 66Good quality (B) · 66 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. | 25.0 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. | 44.2 tok/s | Slowheavy RAM offload |
| Llama 4 Scout 17B-16E | 69Good quality (B) · 69 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. | 3.1 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 |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow | 56Good quality (B) · 56 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. | 3.5 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 75/100 (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 Large Thinking (400B-A13B) | 67Good quality (B) · 67 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. | 6.4 tok/s | Slowtight fit | 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 |
| Hermes 4 405B | 67Good quality (B) · 67 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. | 0.2 tok/s | Very slowtight fit | 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 |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 50Fair quality (C) · 50 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. | 74.6 tok/s | Runs welloffloads to RAM |
| Ling 2.6 Flash (104B-A7.4B) | 67Good quality (B) · 67 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. | 11.0 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 |
| GLM-4.5 (355B-A32B) | 57Good quality (B) · 57 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. | 3.3 tok/s | 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 |
| DeepSeek Coder V2 Instruct (0614) | 68Good quality (B) · 68 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. | 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 |
| gpt-oss 20B | 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 18.3 tok/s | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 46.7 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| Gemma 4 12B | 82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 78Great quality (A) · 78 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. | 29.8 tok/s | Runs welltight fit |
| 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| Qwen2.5 72B Instruct | 73Great quality (A) · 73 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. | 0.5 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 |
| 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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 67/100 (quality, fit, speed and memory use) sets the ranking. | 31.3 tok/s | Slowheavy RAM offload |
| Ring Flash 2.0 (100B-A6B) | 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. | 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 |
| Leanstral 119B-A6B | 62Good quality (B) · 62 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. | 12.5 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 |
| Ornith 1.5 122B-A10B | 64Good quality (B) · 64 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. | 10.4 tok/s | Runs well | 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 |
| Tülu 3 405B | 63Good quality (B) · 63 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. | 0.2 tok/s | Very slowtight fit | 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 |
| MiniMax-M1 80K | 58Good quality (B) · 58 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. | 2.3 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 |
| 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 56Good quality (B) · 56 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. | 75.1 tok/s | Runs welloffloads to RAM |
| Qwen3.5 122B-A10B | 64Good quality (B) · 64 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. | 10.4 tok/s | Runs well | 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 |
| Qwen3.8 27B | 80Great quality (A) · 80 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. | 3.0 tok/s | Slow | 66Good quality (B) · 66 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. | 11.5 tok/s | Runs welloffloads to RAM |
| MiniMax-M1 40K | 57Good quality (B) · 57 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. | 2.3 tok/s | Very slowtight fit | 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 |
| InternVL3.5 241B-A28B | 60Good quality (B) · 60 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. | 3.8 tok/s | 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 |
| Seed-OSS 36B Instruct | 79Great quality (A) · 79 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. | 1.3 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | Slowheavy RAM offload |
| 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 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 |
| 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 43.0 tok/s | Runs great | 59Good quality (B) · 59 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. | 113 tok/s | Runs great |
| Qwen3.6 27B | 78Great quality (A) · 78 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. | 3.0 tok/s | Slow | 65Good quality (B) · 65 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. | 11.5 tok/s | Runs welloffloads to RAM |
| Hermes 4.3 36B | 78Great quality (A) · 78 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. | 1.3 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. | 4.1 tok/s | Slowheavy RAM offload |
| Laguna S 2.1 (118B-A8B) | 72Great quality (A) · 72 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. | 10.2 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 |
| 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 72/100 (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 70B Instruct | 70Great quality (A) · 70 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 | 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 |
| 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 38.3 tok/s | Runs great | 49Fair quality (C) · 49 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. | 176 tok/s | Runs welltight fit |
| Jamba 1.5 Large | 58Good quality (B) · 58 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. | 0.9 tok/s | Very slowtight fit | 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 |
| Qwen3.5 27B | 78Great quality (A) · 78 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. | 3.0 tok/s | Slow | 65Good quality (B) · 65 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. | 11.5 tok/s | Runs welloffloads to RAM |
| Kimi Dev 72B | 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 |
| 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 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. | 90.3 tok/s | Runs welloffloads to RAM |
| 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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. | 33.1 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 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. | 33.1 tok/s | Slowheavy RAM offload |
| Llama 3.1 405B Instruct | 60Good quality (B) · 60 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. | 0.2 tok/s | Very slowtight fit | 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 |
| QVQ 72B Preview | 68Good quality (B) · 68 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 | 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 |
| Nemotron 3.5 Bolt 74B-A9B | 64Good quality (B) · 64 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. | 11.5 tok/s | Runs well | 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 |
| 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| Qwen3 Coder 480B-A35B | 63Good quality (B) · 63 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. | 3.0 tok/s | 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 38B | 75Great quality (A) · 75 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. | 1.2 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. | 3.8 tok/s | Slowheavy RAM offload |
| MiniMax-Text-01 | 53Fair quality (C) · 53 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. | 2.3 tok/s | Very slowtight fit | 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 |
| TMax 27B | 75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (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 Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 11.9 tok/s | Runs welloffloads to RAM |
| Gemma 4 E2B | 58Good quality (B) · 58 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. | 28.5 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. | 78.9 tok/s | Runs great |
| 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 14.5 tok/s | Runs well | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 54.9 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 53Fair quality (C) · 53 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. | 69.1 tok/s | Runs welloffloads to RAM |
| 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 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. | 35.1 tok/s | Slowheavy RAM offload |
| Apertus v1.5 70B | 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. | 0.5 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 16.4 tok/s | Runs well | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 45.6 tok/s | Runs great |
| Nanbeige4.2 3B | 64Good quality (B) · 64 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. | 15.7 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. | 43.5 tok/s | Runs great |
| Fara 1.5 27B | 73Great quality (A) · 73 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. | 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 65/100 (quality, fit, speed and memory use) sets the ranking. | 11.9 tok/s | Runs welloffloads to RAM |
| Mixtral 8x22B Instruct | 54Fair quality (C) · 54 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. | 1.2 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 |
| LFM3 1.7B | 53Fair quality (C) · 53 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. | 37.8 tok/s | Runs great | 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. | 48.3 tok/s | Runs great |
| Gemma 4 E4B | 64Good quality (B) · 64 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. | 14.5 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. | 54.9 tok/s | Runs great |
| Qwen2-VL 72B Instruct | 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. | 0.5 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 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 |
| 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 40.4 tok/s | Runs great | 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. | 159 tok/s | Runs welltight fit |
| NorthCUA Mini | 56Good quality (B) · 56 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. | 20.3 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 35.1 tok/s | Slowheavy RAM offload |
| UI-Mate 27B | 72Great quality (A) · 72 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. | 3.1 tok/s | Slow | 60Good quality (B) · 60 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. | 11.9 tok/s | Runs welloffloads to RAM |
| 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 15.9 tok/s | Runs well | 66Good quality (B) · 66 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. | 44.1 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 26.0 tok/s | Runs well | 60Good quality (B) · 60 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. | 72.0 tok/s | Runs great |
| Apriel 1.5 15B Thinker | 71Great quality (A) · 71 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. | 3.1 tok/s | Slow | 60Good quality (B) · 60 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. | 31.0 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 26.0 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. | 80.2 tok/s | Runs welloffloads to RAM |
| 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 38.0 tok/s | Runs great | 51Fair quality (C) · 51 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. | 103 tok/s | Runs great |
| 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 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. | 103 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 24.1 tok/s | Runs well | 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. | 83.4 tok/s | Runs welltight fit |
| InternVL3 38B | 69Good quality (B) · 69 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 | 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. | 3.8 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 69.5 tok/s | Runs welloffloads to RAM |
| Qwen1.5 110B Chat | 52Fair quality (C) · 52 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 | 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 |
| Phi-4 Reasoning Vision 15B | 69Good quality (B) · 69 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. | 3.0 tok/s | Slow | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 38.7 tok/s | Runs welltight fit |
| 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 39Basic quality (D) · 39 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. | 121 tok/s | Runs welltight fit |
| Nanbeige4.3 33B | 66Good quality (B) · 66 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. | 3.2 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Qwen3 14B | 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. | 3.1 tok/s | Slow | 57Good quality (B) · 57 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. | 31.1 tok/s | Runs welltight fit |
| TMax 4B | 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. | 15.5 tok/s | Runs well | 61Good quality (B) · 61 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. | 43.1 tok/s | Runs great |
| Qwen3.5 4B | 58Good quality (B) · 58 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. | 14.0 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. | 38.9 tok/s | Runs great |
| Sarvam 105B | 52Fair quality (C) · 52 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. | 10.4 tok/s | Runs well | 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 |
| Grok-1 (314B) | 47Fair quality (C) · 47 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. | 0.8 tok/s | Very slowtight fit | 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 |
| LFM3-VL 2B | 47Fair quality (C) · 47 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. | 34.1 tok/s | Runs great | 50Fair quality (C) · 50 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. | 43.5 tok/s | Runs great |
| Granite 4.0 H Tiny (7B-A1B) | 43Fair quality (C) · 43 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. | 39.0 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. | 131 tok/s | Runs great |
| Agents-A1 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. | 14.4 tok/s | Runs well | 60Good quality (B) · 60 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. | 40.0 tok/s | Runs great |
| Hermes 4 14B | 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. | 3.1 tok/s | Slow | 55Good quality (B) · 55 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. | 31.2 tok/s | Runs welltight fit |
| Apertus 70B Instruct | 59Good quality (B) · 59 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. | 0.6 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 |
| Muse Glimmer 30B | 64Good quality (B) · 64 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. | 3.6 tok/s | Slow | 64Good quality (B) · 64 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. | 10.5 tok/s | Runs welloffloads to RAM |
| Devstral Small 2 (24B) | 63Good quality (B) · 63 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. | 3.5 tok/s | Slow | 53Fair quality (C) · 53 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. | 14.2 tok/s | Runs welloffloads to RAM |
| Gemma 4 31B | 63Good quality (B) · 63 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. | 3.4 tok/s | 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. | 3.7 tok/s | Slowheavy RAM offload |
| 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 14.4 tok/s | Runs well | 58Good quality (B) · 58 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. | 40.0 tok/s | Runs great |
| Ministral 3 14B | 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. | 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Runs welltight fit |
| Phi-4 (14B) | 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. | 3.1 tok/s | Slow | 53Fair quality (C) · 53 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. | 31.3 tok/s | Runs welltight fit |
| InternVL3 14B | 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. | 3.0 tok/s | Slow | 44Fair quality (C) · 44 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. | 38.7 tok/s | Runs welltight fit |
| K2 Horizon 7B | 56Good quality (B) · 56 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. | 11.9 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 94/100 (quality, fit, speed and memory use) sets the ranking. | 39.6 tok/s | Runs great |
| Llama 3 70B Instruct | 57Good quality (B) · 57 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. | 0.6 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 |
| Snowflake Arctic Instruct | 35Basic quality (D) · 35 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. | 6.2 tok/s | Slowtight fit | 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 |
| 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 65/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 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. | 52.2 tok/s | Runs great |
| Qwen2.5 14B Instruct | 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. | 3.1 tok/s | Slow | 52Fair quality (C) · 52 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. | 31.3 tok/s | Runs welltight fit |
| 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 65/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 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. | 103 tok/s | Runs welltight fit |
| 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 16.3 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. | 45.1 tok/s | Runs great |
| SenseNova Loop 9B Preview | 54Fair quality (C) · 54 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. | 11.1 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 92/100 (quality, fit, speed and memory use) sets the ranking. | 36.9 tok/s | Runs great |
| Gemma 3 27B IT | 60Good quality (B) · 60 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 | 50Fair quality (C) · 50 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. | 11.4 tok/s | Runs welloffloads to RAM |
| Phi-4 Reasoning Plus (14B) | 71Great quality (A) · 71 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. | 3.1 tok/s | Slow | 60Good quality (B) · 60 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. | 31.4 tok/s | Runs welltight fit |
| Ornith 1.5 9B | 53Fair quality (C) · 53 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. | 11.1 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 92/100 (quality, fit, speed and memory use) sets the ranking. | 36.9 tok/s | Runs great |
| 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 14.7 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. | 40.9 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 17.9 tok/s | Runs well | 52Fair quality (C) · 52 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. | 49.6 tok/s | Runs great |
| Gemma 3 12B IT | 59Good quality (B) · 59 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. | 3.7 tok/s | Slow | 57Good quality (B) · 57 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. | 29.2 tok/s | Runs welltight fit |
| Qwen3.5 9B | 53Fair quality (C) · 53 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. | 11.1 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 36.9 tok/s | Runs great |
| Qwen2.5 14B Instruct 1M | 59Good quality (B) · 59 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. | 3.1 tok/s | Slow | 50Fair quality (C) · 50 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. | 31.2 tok/s | Runs welltight fit |
| Devstral Small 1.1 (24B) | 58Good quality (B) · 58 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. | 3.6 tok/s | Slow | 49Fair quality (C) · 49 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. | 14.9 tok/s | Runs welloffloads to RAM |
| Magistral Small 2507 | 58Good quality (B) · 58 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. | 3.6 tok/s | Slow | 49Fair quality (C) · 49 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. | 14.9 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 42.2 tok/s | Runs great | 40Fair quality (C) · 40 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. | 53.9 tok/s | Runs great |
| MedGemma 27B Text IT | 58Good quality (B) · 58 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 | 49Fair quality (C) · 49 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. | 11.8 tok/s | Runs welloffloads to RAM |
| Ornith 1.0 9B | 52Fair quality (C) · 52 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. | 11.1 tok/s | Runs well | 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. | 36.9 tok/s | Runs great |
| TMax 9B | 51Fair quality (C) · 51 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. | 12.0 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 39.8 tok/s | Runs great |
| Phi-4 Reasoning (14B) | 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. | 3.1 tok/s | Slow | 58Good quality (B) · 58 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. | 31.4 tok/s | Runs welltight fit |
| Phi-3.5 MoE (42B-A6.6B) | 47Fair quality (C) · 47 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. | 12.3 tok/s | Runs well | 53Fair quality (C) · 53 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. | 15.4 tok/s | Slowheavy RAM offload |
| Nous Hermes 2 Mixtral 8x7B DPO | 51Fair quality (C) · 51 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. | 3.5 tok/s | Slow | 49Fair quality (C) · 49 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. | 7.8 tok/s | Slowheavy RAM offload |
| Magistral Small 2506 | 57Good quality (B) · 57 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. | 3.6 tok/s | Slow | 47Fair quality (C) · 47 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. | 14.9 tok/s | Runs welloffloads to RAM |
| EXAONE 4.5 33B | 57Good quality (B) · 57 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. | 3.1 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Mistral Small 3.2 24B | 57Good quality (B) · 57 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. | 3.5 tok/s | Slow | 47Fair quality (C) · 47 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. | 14.2 tok/s | Runs welloffloads to RAM |
| LFM2 8B-A1B | 36Basic quality (D) · 36 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. | 38.0 tok/s | Runs great | 37Basic quality (D) · 37 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. | 103 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 103 tok/s | Runs welltight fit |
| Qwen3 4B | 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. | 16.3 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. | 45.1 tok/s | Runs great |
| Qwen2 57B-A14B Instruct | 49Fair quality (C) · 49 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. | 3.2 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. | 9.5 tok/s | Slowheavy RAM offload |
| 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 16.5 tok/s | Runs well | 50Fair quality (C) · 50 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. | 45.7 tok/s | Runs great |
| Terminal RSI 27B | 57Good quality (B) · 57 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. | 3.0 tok/s | Slow | 47Fair quality (C) · 47 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. | 11.5 tok/s | Runs welloffloads to RAM |
| North Micro Vision | 41Fair quality (C) · 41 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. | 26.4 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 34.8 tok/s | Runs great | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great |
| MiniCPM5 1B | 35Basic quality (D) · 35 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. | 42.0 tok/s | Runs great | 36Basic quality (D) · 36 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. | 77.4 tok/s | Runs great |
| Hemmingway 1.5 | 56Good quality (B) · 56 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. | 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 12.5 tok/s | Runs welloffloads to RAM |
| Qwen3 8B | 50Fair quality (C) · 50 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. | 10.3 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 43.5 tok/s | Runs great |
| Mistral Small 3.1 24B | 55Good quality (B) · 55 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. | 3.5 tok/s | Slow | 46Fair quality (C) · 46 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. | 14.2 tok/s | Runs welloffloads to RAM |
| 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 24.2 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 67.2 tok/s | Runs great |
| Mixtral 8x7B Instruct | 49Fair quality (C) · 49 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. | 3.5 tok/s | Slow | 47Fair quality (C) · 47 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. | 7.8 tok/s | Slowheavy RAM offload |
| Qwen3-VL 32B Instruct | 54Fair quality (C) · 54 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. | 3.2 tok/s | Slow | 74Great quality (A) · 74 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. | 3.3 tok/s | Slowheavy RAM offload |
| 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 19.2 tok/s | Runs well | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 53.4 tok/s | Runs great |
| Unlimited OCR 2 (3B-A0.6B) | 44Fair quality (C) · 44 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. | 45.8 tok/s | Runs great | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 86.6 tok/s | Runs great |
| Granite 4.2 8B | 47Fair quality (C) · 47 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. | 12.2 tok/s | Runs well | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 40.5 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 25.0 tok/s | Runs well | 43Fair quality (C) · 43 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. | 118 tok/s | Runs welltight fit |
| Jamba 1.5 Mini | 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. | 5.4 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. | 11.6 tok/s | Slowheavy RAM offload |
| MiMo-VL 7B RL | 48Fair quality (C) · 48 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. | 10.2 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 84/100 (quality, fit, speed and memory use) sets the ranking. | 42.9 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 28.8 tok/s | Runs well | 40Fair quality (C) · 40 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. | 79.9 tok/s | Runs great |
| Mistral Small 3 24B (2501) | 53Fair quality (C) · 53 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. | 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 14.9 tok/s | Runs welloffloads to RAM |
| Ministral 3 14B Reasoning | 65Good quality (B) · 65 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. | 3.3 tok/s | Slow | 55Good quality (B) · 55 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. | 33.0 tok/s | Runs welltight fit |
| 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 25.0 tok/s | Runs well | 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. | 118 tok/s | Runs welltight fit |
| AceReason Nemotron 14B | 65Good quality (B) · 65 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. | 3.1 tok/s | Slow | 55Good quality (B) · 55 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. | 31.2 tok/s | Runs welltight fit |
| OpenReasoning Nemotron 14B | 65Good quality (B) · 65 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. | 3.1 tok/s | Slow | 55Good quality (B) · 55 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. | 31.2 tok/s | Runs welltight fit |
| Qwen2.5 Coder 14B Instruct | 65Good quality (B) · 65 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. | 3.1 tok/s | Slow | 55Good quality (B) · 55 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. | 31.2 tok/s | Runs welltight fit |
| Apriel Nemotron 15B Thinker | 65Good quality (B) · 65 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. | 3.0 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. | 39.1 tok/s | Runs welltight fit |
| 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 21.0 tok/s | Runs well | 44Fair quality (C) · 44 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. | 58.1 tok/s | Runs great |
| 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 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. | 52.2 tok/s | Runs great |
| Granite 4.2 30B | 53Fair quality (C) · 53 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. | 3.7 tok/s | Slow | 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slowheavy RAM offload |
| Qwen3 32B | 53Fair quality (C) · 53 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. | 3.3 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Gemma 3n E4B | 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. | 16.4 tok/s | Runs well | 45Fair quality (C) · 45 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. | 61.8 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 tok/s | Runs well | 44Fair quality (C) · 44 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. | 56.7 tok/s | Runs great |
| MiMo 7B RL | 47Fair quality (C) · 47 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. | 10.8 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. | 37.6 tok/s | Runs great |
| Falcon 180B Chat | 33Basic quality (D) · 33 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. | 0.3 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 | 47Fair quality (C) · 47 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. | 10.7 tok/s | Runs well | 53Fair quality (C) · 53 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. | 44.9 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 32.7 tok/s | Runs great | 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. | 90.7 tok/s | Runs great |
| Dolphin Mistral 24B Venice Edition | 52Fair quality (C) · 52 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. | 3.5 tok/s | Slow | 43Fair quality (C) · 43 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. | 14.2 tok/s | Runs welloffloads to RAM |
| Voxtral Small 24B | 52Fair quality (C) · 52 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. | 3.5 tok/s | Slow | 43Fair quality (C) · 43 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. | 13.8 tok/s | Runs welloffloads to RAM |
| Jamba2 3B | 39Basic quality (D) · 39 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. | 21.6 tok/s | Runs well | 42Fair quality (C) · 42 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. | 59.9 tok/s | Runs great |
| LFM2.5 1.2B Instruct | 31Basic quality (D) · 31 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. | 38.8 tok/s | Runs great | 32Basic quality (D) · 32 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. | 71.5 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 21.2 tok/s | Runs well | 42Fair quality (C) · 42 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. | 58.9 tok/s | Runs great |
| Gemma 2 27B IT | 52Fair quality (C) · 52 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. | 3.1 tok/s | Slow | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 4.5 tok/s | Slowheavy RAM offload |
| DeepCoder 14B Preview | 63Good quality (B) · 63 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. | 3.1 tok/s | Slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 31.2 tok/s | Runs welltight fit |
| GLM-4 32B 0414 | 51Fair quality (C) · 51 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. | 3.3 tok/s | 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. | 3.7 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 17.0 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. | 47.2 tok/s | Runs great |
| Ministral 3 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. | 17.0 tok/s | Runs well | 44Fair quality (C) · 44 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. | 47.1 tok/s | Runs great |
| Granite 4.0 H Small (32B-A9B) | 43Fair quality (C) · 43 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. | 11.5 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 13.2 tok/s | Slowheavy RAM offload |
| Mistral Nemo 12B Instruct | 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 | 43Fair quality (C) · 43 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. | 37.8 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 16.3 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. | 45.1 tok/s | Runs great |
| Qwen2.5-Math 72B Instruct | 57Good quality (B) · 57 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. | 0.6 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 |
| PaddleOCR-VL 1.6 0.9B | 41Fair quality (C) · 41 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. | 47.3 tok/s | Runs great | 42Fair quality (C) · 42 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. | 87.1 tok/s | Runs great |
| Reka Flash 3.1 (21B) | 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. | 3.1 tok/s | Slow | 55Good quality (B) · 55 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. | 12.2 tok/s | Runs welloffloads to RAM |
| 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 15.2 tok/s | Runs well | 45Fair quality (C) · 45 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. | 42.2 tok/s | Runs great |
| Qwen3-VL 2B Instruct | 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 39.7 tok/s | Runs great | 36Basic quality (D) · 36 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. | 85.2 tok/s | Runs great |
| Granite 4.1 30B | 50Fair quality (C) · 50 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. | 3.7 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. | 3.1 tok/s | Slowheavy RAM offload |
| Llama 3.1 Nemotron Nano 8B v1 | 45Fair quality (C) · 45 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 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. | 44.4 tok/s | Runs great |
| Solar Pro Preview 22B | 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow | 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. | 17.7 tok/s | Runs welloffloads to RAM |
| Dolphin 3.0 R1 Mistral 24B | 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow | 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. | 14.9 tok/s | Runs welloffloads to RAM |
| MiniCPM4 8B | 45Fair quality (C) · 45 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 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 82/100 (quality, fit, speed and memory use) sets the ranking. | 43.5 tok/s | Runs great |
| MiniCPM-OCR 1.0 1.3B | 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. | 41.6 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. | 64.3 tok/s | Runs great |
| InternVL3.5 8B | 43Fair quality (C) · 43 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. | 12.6 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 86/100 (quality, fit, speed and memory use) sets the ranking. | 41.8 tok/s | Runs great |
| Unlimited OCR (3B-A0.6B) | 40Fair quality (C) · 40 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. | 45.8 tok/s | Runs great | 40Fair quality (C) · 40 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. | 86.6 tok/s | Runs great |
| EXAONE 4.0 32B | 50Fair quality (C) · 50 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. | 3.4 tok/s | 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. | 3.8 tok/s | Slowheavy RAM offload |
| Olmo 3.1 32B Instruct | 50Fair quality (C) · 50 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. | 3.3 tok/s | 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 |
| MedGemma 4B IT | 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. | 15.2 tok/s | Runs well | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 42.2 tok/s | Runs great |
| Qwen3-VL 8B Instruct | 43Fair quality (C) · 43 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. | 12.3 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 86/100 (quality, fit, speed and memory use) sets the ranking. | 40.6 tok/s | Runs great |
| EXAONE 4.0 1.2B | 29Basic quality (D) · 29 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. | 42.2 tok/s | Runs great | 30Basic quality (D) · 30 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. | 65.3 tok/s | Runs great |
| 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 14.5 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. | 40.2 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 14B | 61Good quality (B) · 61 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. | 3.1 tok/s | Slow | 52Fair quality (C) · 52 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. | 31.2 tok/s | Runs welltight fit |
| JanusCoder 14B | 61Good quality (B) · 61 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. | 3.1 tok/s | Slow | 52Fair quality (C) · 52 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. | 31.2 tok/s | Runs welltight fit |
| Hunyuan 7B Instruct | 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 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 82/100 (quality, fit, speed and memory use) sets the ranking. | 39.2 tok/s | Runs great |
| MiMo V2.6 Distill Qwen 9B | 54Fair quality (C) · 54 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. | 11.4 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 87/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| Magistral Small 1.2 (24B) | 60Good quality (B) · 60 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. | 3.5 tok/s | Slow | 50Fair quality (C) · 50 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. | 14.2 tok/s | Runs welloffloads to RAM |
| Qwen2.5 7B Instruct | 43Fair quality (C) · 43 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. | 11.1 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 82/100 (quality, fit, speed and memory use) sets the ranking. | 38.6 tok/s | Runs great |
| Baichuan M2 32B | 49Fair quality (C) · 49 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. | 3.3 tok/s | Slow | 66Good quality (B) · 66 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 | Slowheavy RAM offload |
| Qwen2.5 32B Instruct | 49Fair quality (C) · 49 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. | 3.3 tok/s | Slow | 66Good quality (B) · 66 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 | 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 19.2 tok/s | Runs well | 40Fair quality (C) · 40 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. | 53.4 tok/s | Runs great |
| Pixtral 12B (2409) | 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. | 5.3 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. | 37.1 tok/s | Runs welltight fit |
| MiniCPM-V 4.5 8B | 42Fair quality (C) · 42 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. | 12.4 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 41.0 tok/s | Runs great |
| Qwen2.5-VL 7B Instruct | 43Fair quality (C) · 43 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. | 10.2 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. | 43.0 tok/s | Runs great |
| Granite 4.1 8B | 42Fair quality (C) · 42 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. | 12.2 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 40.5 tok/s | Runs great |
| Hunyuan 4B Instruct | 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. | 15.5 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. | 43.0 tok/s | Runs great |
| Nemotron Nano 9B v2 | 42Fair quality (C) · 42 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. | 12.1 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great |
| Olmo 3 7B Instruct | 42Fair quality (C) · 42 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. | 11.6 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. | 40.3 tok/s | Runs great |
| 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 17.1 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. | 47.5 tok/s | Runs great |
| Phi-4 Multimodal Instruct | 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. | 11.7 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. | 44.4 tok/s | Runs great |
| TeleOCR | 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. | 46.1 tok/s | Runs great | 40Fair quality (C) · 40 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. | 58.9 tok/s | Runs great |
| Falcon-H1 7B Instruct | 42Fair quality (C) · 42 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. | 11.1 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. | 38.8 tok/s | Runs great |
| Qwen2.5-VL 32B Instruct | 47Fair quality (C) · 47 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. | 3.2 tok/s | Slow | 64Good quality (B) · 64 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. | 3.3 tok/s | Slowheavy RAM offload |
| Qwen2.5 7B Instruct 1M | 42Fair quality (C) · 42 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. | 11.1 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. | 38.6 tok/s | Runs great |
| 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 tok/s | Runs well | 38Basic quality (D) · 38 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. | 56.9 tok/s | Runs great |
| Foundation-Sec 1.1 8B Instruct | 42Fair quality (C) · 42 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. | 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. | 44.4 tok/s | Runs great |
| InternVL2.5 8B | 42Fair quality (C) · 42 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. | 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. | 44.1 tok/s | Runs great |
| 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 44.8 tok/s | Runs great | 28Basic quality (D) · 28 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. | 57.3 tok/s | Runs great |
| GLiDE 9B | 42Fair quality (C) · 42 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. | 10.7 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 80/100 (quality, fit, speed and memory use) sets the ranking. | 44.9 tok/s | Runs great |
| InternLM2.5 20B Chat | 47Fair quality (C) · 47 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. | 3.3 tok/s | Slow | 42Fair quality (C) · 42 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. | 12.6 tok/s | Runs welloffloads to RAM |
| GLM-4.1V 9B Thinking | 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. | 10.4 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. | 34.6 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 25.5 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 70.6 tok/s | Runs great |
| 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. | 52.2 tok/s | Runs great | 26Basic quality (D) · 26 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. | 96.1 tok/s | Runs great |
| 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 43.0 tok/s | Runs great | 25Basic quality (D) · 25 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. | 113 tok/s | Runs great |
| DeepSeek R1 0528 Qwen3 8B | 52Fair quality (C) · 52 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. | 10.3 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 43.5 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 41.7 tok/s | Runs great | 30Basic quality (D) · 30 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. | 41.2 tok/s | Runs great |
| LFM2 1.2B | 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. | 38.8 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. | 71.5 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 20.8 tok/s | Runs well | 36Basic quality (D) · 36 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. | 57.6 tok/s | Runs great |
| AFM 4.5B | 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. | 14.2 tok/s | Runs well | 40Fair quality (C) · 40 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. | 39.3 tok/s | Runs great |
| Ministral 3 8B | 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. | 12.0 tok/s | Runs well | 53Fair quality (C) · 53 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. | 39.9 tok/s | Runs great |
| Hermes 3 (Llama 3.1 8B) | 40Fair quality (C) · 40 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Llama 3.1 8B Instruct | 40Fair quality (C) · 40 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Mistral Small 22B (2409) | 45Fair quality (C) · 45 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 | Slow | 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. | 15.4 tok/s | Runs welloffloads to RAM |
| MiniCPM-V 2.6 8B | 40Fair quality (C) · 40 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. | 10.4 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. | 44.0 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well | 37Basic quality (D) · 37 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. | 59.6 tok/s | Runs great |
| Falcon-H1 1.5B Instruct | 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. | 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 53.9 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 16.1 tok/s | Runs well | 38Basic quality (D) · 38 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. | 44.6 tok/s | Runs great |
| 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 20.4 tok/s | Runs well | 35Basic quality (D) · 35 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. | 56.5 tok/s | Runs great |
| Falcon-H1 34B Instruct | 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. | 3.2 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Falcon 3 7B Instruct | 38Basic quality (D) · 38 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. | 11.3 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. | 39.5 tok/s | Runs great |
| 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 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Runs welltight fit |
| 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 17.1 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 47.5 tok/s | Runs great |
| 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 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 33.0 tok/s | Runs welltight fit |
| Devstral Small 2505 | 55Good quality (B) · 55 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. | 3.6 tok/s | Slow | 46Fair quality (C) · 46 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. | 14.9 tok/s | Runs welloffloads to RAM |
| EXAONE 3.5 7.8B | 38Basic quality (D) · 38 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. | 10.8 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. | 45.6 tok/s | Runs great |
| 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 21.2 tok/s | Runs well | 34Basic quality (D) · 34 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. | 58.7 tok/s | Runs great |
| Ministral 8B (2410) | 38Basic quality (D) · 38 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. | 10.5 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. | 44.4 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 17.1 tok/s | Runs well | 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 47.5 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 13.8 tok/s | Runs well | 49Fair quality (C) · 49 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. | 52.2 tok/s | Runs great |
| DeepHermes 3 Llama 3 8B Preview | 38Basic quality (D) · 38 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Dolphin 3.0 Llama 3.1 8B | 38Basic quality (D) · 38 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Tülu 3 8B | 38Basic quality (D) · 38 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. | 10.5 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. | 44.4 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 35.1 tok/s | Runs great | 30Basic quality (D) · 30 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. | 75.3 tok/s | Runs great |
| Granite 3.2 8B Instruct | 38Basic quality (D) · 38 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. | 10.4 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. | 43.6 tok/s | Runs great |
| Granite 3.3 8B | 38Basic quality (D) · 38 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. | 10.4 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. | 43.6 tok/s | Runs great |
| SenseNova 6.8 Code2Video | 55Good quality (B) · 55 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. | 3.1 tok/s | Slow | 46Fair quality (C) · 46 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. | 11.9 tok/s | Runs welloffloads to RAM |
| UI-Mate 9B | 49Fair quality (C) · 49 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. | 11.4 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 84/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| UI-Venus 2 9B | 49Fair quality (C) · 49 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. | 11.4 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 84/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| DeepSeek LLM 67B Chat | 39Basic quality (D) · 39 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. | 0.7 tok/s | Very slow | 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking. | 2.5 tok/s | Very slowheavy RAM offload |
| QwQ 32B | 54Fair quality (C) · 54 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. | 3.3 tok/s | Slow | 74Great quality (A) · 74 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. | 3.4 tok/s | Slowheavy RAM offload |
| Qwen2.5 1.5B Instruct | 22Basic quality (D) · 22 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. | 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 65/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs great |
| LFM2-VL 1.6B | 22Basic quality (D) · 22 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. | 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 65/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs great |
| Command R (08-2024) 32B | 43Fair quality (C) · 43 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. | 3.3 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. | 3.6 tok/s | Slowheavy RAM offload |
| Granite 3.2 2B Instruct | 25Basic quality (D) · 25 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. | 33.4 tok/s | Runs great | 30Basic quality (D) · 30 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. | 71.7 tok/s | Runs great |
| Granite 3.3 2B | 25Basic quality (D) · 25 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. | 33.4 tok/s | Runs great | 30Basic quality (D) · 30 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. | 71.7 tok/s | Runs great |
| 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 4.8 tok/s | Slow | 30Basic quality (D) · 30 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. | 42.7 tok/s | Runs welltight fit |
| Phi-3 Small 8K Instruct | 36Basic quality (D) · 36 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. | 11.4 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 39.8 tok/s | Runs great |
| MiniCPM-o 2.6 8B | 36Basic quality (D) · 36 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. | 12.4 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. | 41.1 tok/s | Runs great |
| Seed-Coder 8B Reasoning | 48Fair quality (C) · 48 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. | 10.3 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 43.2 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 14.0 tok/s | Runs well | 36Basic quality (D) · 36 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. | 53.1 tok/s | Runs great |
| Qwen2 7B 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. | 11.1 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. | 38.6 tok/s | Runs great |
| Dolphin 2.9.4 Llama 3.1 8B | 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Hermes 2 Pro Llama 3 8B | 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. | 10.5 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. | 44.4 tok/s | Runs great |
| OpenChat 3.6 8B | 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. | 10.5 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. | 44.4 tok/s | Runs great |
| LightOnOCR-3 4B | 45Fair quality (C) · 45 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. | 14.4 tok/s | Runs well | 48Fair quality (C) · 48 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. | 40.0 tok/s | Runs great |
| InternVL2 8B | 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. | 10.5 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. | 44.1 tok/s | Runs great |
| GLM-4 9B 0414 | 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. | 11.4 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| Granite 3.1 8B 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. | 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. | 43.6 tok/s | Runs great |
| NorthCUA Nano | 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. | 11.4 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 17.0 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. | 47.2 tok/s | Runs great |
| OpenReasoning Nemotron 32B | 53Fair quality (C) · 53 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. | 3.3 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Skywork OR1 32B | 53Fair quality (C) · 53 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. | 3.3 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| Command R7B | 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Llama 3.2 1B Instruct | 21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 43.6 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. | 67.4 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 17.5 tok/s | Runs well | 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 48.4 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 20.4 tok/s | Runs well | 32Basic quality (D) · 32 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. | 56.5 tok/s | Runs great |
| Qwen2-VL 7B 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. | 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 43.0 tok/s | Runs great |
| Aya Expanse 32B | 42Fair quality (C) · 42 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. | 3.3 tok/s | 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. | 3.6 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 14.0 tok/s | Runs well | 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 52.8 tok/s | Runs great |
| Olmo 3.1 32B Think | 53Fair quality (C) · 53 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. | 3.3 tok/s | Slow | 72Great quality (A) · 72 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. | 3.7 tok/s | Slowheavy RAM offload |
| Aya Vision 32B | 42Fair quality (C) · 42 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. | 3.2 tok/s | 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. | 3.5 tok/s | Slowheavy RAM offload |
| OLMo 2 32B Instruct | 42Fair quality (C) · 42 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. | 3.3 tok/s | 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. | 3.7 tok/s | Slowheavy RAM offload |
| Falcon 3 10B 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. | 10.4 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 80/100 (quality, fit, speed and memory use) sets the ranking. | 34.6 tok/s | Runs welltight fit |
| 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well | 33Basic quality (D) · 33 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. | 59.6 tok/s | Runs great |
| Falcon-H1R 7B | 47Fair quality (C) · 47 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. | 11.1 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 38.8 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 33.4 tok/s | Runs great | 28Basic quality (D) · 28 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. | 71.7 tok/s | Runs great |
| EXAONE Deep 7.8B | 47Fair quality (C) · 47 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. | 10.8 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. | 37.6 tok/s | Runs great |
| InternLM3 8B Instruct | 35Basic quality (D) · 35 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. | 12.2 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. | 40.5 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 34.7 tok/s | Runs great | 27Basic quality (D) · 27 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. | 74.3 tok/s | Runs great |
| Gemma 2 9B IT | 35Basic quality (D) · 35 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. | 11.6 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. | 38.6 tok/s | Runs great |
| Codestral 22B | 52Fair quality (C) · 52 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. | 3.8 tok/s | Slow | 43Fair quality (C) · 43 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. | 15.4 tok/s | Runs welloffloads to RAM |
| Seed-Coder 8B Instruct | 47Fair quality (C) · 47 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. | 10.3 tok/s | Runs well | 53Fair quality (C) · 53 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. | 43.2 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 32.4 tok/s | Runs great | 28Basic quality (D) · 28 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. | 69.5 tok/s | Runs great |
| Granite 3.1 3B-A800M Instruct | 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 47.1 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. | 71.7 tok/s | Runs great |
| Chandra OCR 2 | 45Fair quality (C) · 45 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. | 12.3 tok/s | Runs well | 47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 46.6 tok/s | Runs great |
| EXAONE Deep 32B | 51Fair quality (C) · 51 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 | 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. | 3.5 tok/s | Slowheavy RAM offload |
| Qwen2.5 Coder 7B Instruct | 46Fair quality (C) · 46 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. | 11.1 tok/s | Runs well | 53Fair quality (C) · 53 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. | 38.6 tok/s | Runs great |
| Llama 3 8B Instruct | 35Basic quality (D) · 35 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Command R7B Arabic | 35Basic quality (D) · 35 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Gemma 3 1B | 19Basic quality (D) · 19 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. | 45.4 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. | 83.6 tok/s | Runs great |
| Olmo 3 7B Think | 45Fair quality (C) · 45 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. | 11.6 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 40.3 tok/s | Runs great |
| GLM-Z1 32B (0414) | 51Fair quality (C) · 51 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. | 3.3 tok/s | 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. | 3.7 tok/s | Slowheavy RAM offload |
| Mistral-NeMo-Minitron 8B Instruct | 35Basic quality (D) · 35 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. | 10.1 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. | 42.4 tok/s | Runs great |
| Hunyuan 1.8B Instruct | 20Basic quality (D) · 20 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. | 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 46.7 tok/s | Runs great |
| SmolVLM2 2.2B 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. | 37.6 tok/s | Runs great | 24Basic quality (D) · 24 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. | 80.6 tok/s | Runs great |
| Qwen2-VL 2B 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. | 38.3 tok/s | Runs great | 24Basic quality (D) · 24 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. | 82.1 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 55/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well | 30Basic quality (D) · 30 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. | 56.2 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 55/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking. | 2.5 tok/s | Very slowheavy RAM offload |
| OpenReasoning Nemotron 7B | 45Fair quality (C) · 45 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. | 11.1 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 38.6 tok/s | Runs great |
| Command R 35B (v01) | 37Basic quality (D) · 37 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. | 3.1 tok/s | 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 |
| InternLM2 Chat 20B | 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. | 3.3 tok/s | Slow | 29Basic quality (D) · 29 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. | 23.1 tok/s | Runs welloffloads to RAM |
| GLM-4 9B Chat 1M | 33Basic quality (D) · 33 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. | 11.3 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. | 37.6 tok/s | Runs great |
| GLM-4 9B Chat (2024) | 33Basic quality (D) · 33 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 | 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. | 37.9 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 32B | 50Fair quality (C) · 50 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. | 3.3 tok/s | Slow | 68Good quality (B) · 68 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 |
| SmolLM2 1.7B Instruct | 19Basic quality (D) · 19 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. | 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 48.9 tok/s | Runs great |
| InternLM2.5 7B Chat | 33Basic quality (D) · 33 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. | 10.9 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. | 46.0 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 55/100 (quality, fit, speed and memory use) sets the ranking. | 32.2 tok/s | Runs great | 26Basic quality (D) · 26 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. | 69.0 tok/s | Runs great |
| WeVisOne-VL 4B | 42Fair quality (C) · 42 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 | 44Fair quality (C) · 44 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 51.2 tok/s | Runs great |
| Granite 3.0 3B-A800M Instruct | 17Basic quality (D) · 17 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. | 47.1 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. | 71.7 tok/s | Runs great |
| Aya Expanse 8B | 33Basic quality (D) · 33 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Apertus 8B Instruct | 33Basic quality (D) · 33 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. | 10.5 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. | 44.3 tok/s | Runs great |
| Granite 3.0 8B Instruct | 33Basic quality (D) · 33 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. | 10.4 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. | 43.6 tok/s | Runs great |
| Apertus v1.5 8B | 32Basic quality (D) · 32 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. | 12.1 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. | 40.0 tok/s | Runs great |
| LFM2 700M | 18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 45.0 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 113 tok/s | Runs great |
| DeepSeek MoE 16B Chat | 21Basic quality (D) · 21 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. | 27.5 tok/s | Runs well | 18Basic quality (D) · 18 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. | 126 tok/s | Runs welltight fit |
| SmolVLM 2.2B Instruct | 18Basic quality (D) · 18 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. | 37.6 tok/s | Runs great | 22Basic quality (D) · 22 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. | 80.6 tok/s | Runs great |
| Mistral 7B Instruct v0.3 | 31Basic quality (D) · 31 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. | 11.7 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. | 40.6 tok/s | Runs great |
| OpenHands LM 32B | 49Fair quality (C) · 49 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. | 3.3 tok/s | Slow | 66Good quality (B) · 66 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. | 3.4 tok/s | Slowheavy RAM offload |
| Foundation-Sec 8B Reasoning | 43Fair quality (C) · 43 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. | 10.5 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 44.4 tok/s | Runs great |
| Zamba2 7B Instruct | 31Basic quality (D) · 31 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. | 11.5 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. | 40.0 tok/s | Runs great |
| LLM4Decompile 22B V2 | 48Fair quality (C) · 48 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. | 3.8 tok/s | Slow | 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. | 15.4 tok/s | Runs welloffloads to RAM |
| Falcon3 Mamba 7B Instruct | 31Basic quality (D) · 31 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. | 11.6 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. | 40.5 tok/s | Runs great |
| 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 54/100 (quality, fit, speed and memory use) sets the ranking. | 28.4 tok/s | Runs well | 26Basic quality (D) · 26 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. | 60.9 tok/s | Runs great |
| Aya Vision 8B | 30Basic quality (D) · 30 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. | 12.5 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. | 41.3 tok/s | Runs great |
| EXAONE 3.0 7.8B Instruct | 31Basic quality (D) · 31 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. | 10.8 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. | 45.6 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 54/100 (quality, fit, speed and memory use) sets the ranking. | 28.4 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 110 tok/s | Runs welltight fit |
| Dolphin 2.9 Llama 3 8B | 31Basic quality (D) · 31 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. | 10.5 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. | 44.4 tok/s | Runs great |
| Qwen2.5-Omni 7B | 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. | 10.0 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. | 33.2 tok/s | Runs great |
| Aya 23 35B | 35Basic quality (D) · 35 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. | 3.1 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 |
| Code Llama 70B Instruct | 43Fair quality (C) · 43 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. | 0.7 tok/s | Very slow | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 36/100 (quality, fit, speed and memory use) sets the ranking. | 2.5 tok/s | Very slowheavy RAM offload |
| OLMo 2 7B Instruct | 30Basic quality (D) · 30 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. | 11.6 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.3 tok/s | Runs great |
| CogVLM2 Llama 3 Chat 19B | 36Basic quality (D) · 36 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 | Slow | 36Basic quality (D) · 36 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. | 6.0 tok/s | Slowheavy RAM offload |
| Hermes 2 Pro Mistral 7B | 30Basic quality (D) · 30 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. | 11.7 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| Starling LM 7B Beta | 30Basic quality (D) · 30 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. | 11.7 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| DeepSeek R1 Distill Llama 8B | 42Fair quality (C) · 42 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. | 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 44.4 tok/s | Runs great |
| Zamba2 2.7B 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. | 40.4 tok/s | Runs great | 22Basic quality (D) · 22 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. | 68.2 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 44.8 tok/s | Runs great | 18Basic quality (D) · 18 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. | 44.2 tok/s | Runs great |
| Qwen2 1.5B Instruct | 15Basic quality (D) · 15 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. | 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs great |
| Fara 7B | 42Fair quality (C) · 42 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. | 10.2 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. | 43.0 tok/s | Runs great |
| Qwen2.5 Coder 32B Instruct | 46Fair quality (C) · 46 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. | 3.3 tok/s | Slow | 63Good quality (B) · 63 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. | 3.4 tok/s | Slowheavy RAM offload |
| Falcon 3 1B Instruct | 15Basic quality (D) · 15 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. | 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 50.1 tok/s | Runs great |
| OpenChat 3.5 (0106) | 29Basic quality (D) · 29 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. | 11.7 tok/s | Runs well | 33Basic quality (D) · 33 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. | 40.7 tok/s | Runs great |
| GLM-Z1 9B (0414) | 40Fair quality (C) · 40 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. | 11.4 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 37.9 tok/s | Runs great |
| Spark X2.6 1.7B | 15Basic quality (D) · 15 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. | 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 48.9 tok/s | Runs great |
| QwQ 32B Preview | 46Fair quality (C) · 46 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. | 3.3 tok/s | Slow | 62Good quality (B) · 62 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. | 3.4 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 45.0 tok/s | Runs great | 17Basic quality (D) · 17 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. | 44.5 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 21.2 tok/s | Runs well | 36Basic quality (D) · 36 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. | 58.7 tok/s | Runs great |
| Qwen3 0.6B | 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. | 44.4 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 111 tok/s | Runs great |
| Mistral 7B Instruct v0.2 | 28Basic quality (D) · 28 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. | 11.7 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| Nous Hermes 2 Mistral 7B DPO | 28Basic quality (D) · 28 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. | 11.7 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| OpenChat 3.5 (1210) | 28Basic quality (D) · 28 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. | 11.7 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| Yi 1.5 34B Chat | 35Basic quality (D) · 35 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. | 3.1 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| LFM2.5 350M | 14Basic quality (D) · 14 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. | 43.9 tok/s | Runs great | 14Basic quality (D) · 14 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. | 239 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. | 64.1 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. | 161 tok/s | Runs great |
| Qwen2.5-Omni 3B | 28Basic quality (D) · 28 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. | 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 44.6 tok/s | Runs great |
| Llama 3.2 11B Vision Instruct | 29Basic quality (D) · 29 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. | 10.1 tok/s | Runs well | 35Basic quality (D) · 35 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. | 43.2 tok/s | Runs great |
| Qwen2.5 Coder 1.5B Instruct | 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. | 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs great |
| 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 4.6 tok/s | Slow | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | 7.2 tok/s | Slowheavy RAM offload |
| OLMo 2 1B Instruct | 13Basic quality (D) · 13 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. | 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 56.5 tok/s | Runs great |
| Aya 23 8B | 28Basic quality (D) · 28 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. | 10.5 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. | 44.4 tok/s | Runs great |
| SmolLM 1.7B Instruct | 13Basic quality (D) · 13 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. | 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 48.9 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 7B | 38Basic quality (D) · 38 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. | 11.1 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 38.6 tok/s | Runs great |
| OpenHermes 2.5 Mistral 7B | 26Basic quality (D) · 26 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. | 11.7 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| Starling LM 7B Alpha | 26Basic quality (D) · 26 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. | 11.7 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 40.7 tok/s | Runs great |
| DeepScaleR 1.5B Preview | 24Basic quality (D) · 24 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. | 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 47.0 tok/s | Runs great |
| Nous Hermes 2 SOLAR 10.7B | 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. | 10.0 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 33.2 tok/s | Runs great |
| SOLAR 10.7B 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. | 10.0 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 33.2 tok/s | Runs great |
| LFM2 350M | 12Basic quality (D) · 12 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. | 43.9 tok/s | Runs great | 12Basic quality (D) · 12 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. | 239 tok/s | Runs great |
| Granite 4.0 H 350M | 12Basic quality (D) · 12 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. | 45.2 tok/s | Runs great | 12Basic quality (D) · 12 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. | 246 tok/s | Runs great |
| 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. | 74.0 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. | 186 tok/s | Runs great |
| Yi 1.5 6B Chat | 26Basic quality (D) · 26 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. | 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. | 40.8 tok/s | Runs great |
| GLiDE 0.8B | 11Basic quality (D) · 11 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. | 44.4 tok/s | Runs great | 11Basic quality (D) · 11 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. | 111 tok/s | Runs great |
| Yi 1.5 9B Chat | 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. | 12.2 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. | 40.4 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 51/100 (quality, fit, speed and memory use) sets the ranking. | 38.4 tok/s | Runs great | 16Basic quality (D) · 16 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. | 64.8 tok/s | Runs great |
| Phi-2 2.7B | 11Basic quality (D) · 11 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. | 38.7 tok/s | Runs great | 16Basic quality (D) · 16 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. | 65.3 tok/s | Runs great |
| Mistral 7B Instruct v0.1 | 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. | 11.7 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. | 40.7 tok/s | Runs great |
| Falcon Mamba 7B Instruct | 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. | 11.6 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 40.5 tok/s | Runs great |
| Qwen1.5 32B Chat | 30Basic quality (D) · 30 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. | 3.3 tok/s | Slow | 41Fair quality (C) · 41 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. | 3.4 tok/s | Slowheavy RAM offload |
| 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. | 65.3 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. | 164 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. | 68.0 tok/s | Runs great | 10Basic quality (D) · 10 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. | 171 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. | 66.8 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. | 363 tok/s | Runs great |
| LLaVA 1.6 34B | 30Basic quality (D) · 30 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. | 3.1 tok/s | Slow | 41Fair quality (C) · 41 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. | 3.3 tok/s | Slowheavy RAM offload |
| StableLM 2 1.6B Chat | 9Basic quality (D) · 9 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. | 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 51.0 tok/s | Runs great |
| StableLM 2 Zephyr 1.6B | 9Basic quality (D) · 9 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. | 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 51.0 tok/s | Runs great |
| 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 51/100 (quality, fit, speed and memory use) sets the ranking. | 20.2 tok/s | Runs well | 22Basic quality (D) · 22 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. | 43.3 tok/s | Runs great |
| DeepSeek Prover V2 7B | 33Basic quality (D) · 33 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. | 12.2 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 51.6 tok/s | Runs welltight fit |
| Neural Chat 7B v3.3 | 23Basic quality (D) · 23 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. | 11.7 tok/s | Runs well | 27Basic quality (D) · 27 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. | 40.7 tok/s | Runs great |
| RecurrentGemma 9B IT | 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. | 11.2 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 37.0 tok/s | Runs great |
| LLaVA 1.6 Mistral 7B | 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. | 11.2 tok/s | Runs well | 27Basic quality (D) · 27 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. | 38.9 tok/s | Runs great |
| DeepSeek R1 Distill Qwen 1.5B | 20Basic quality (D) · 20 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. | 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 47.0 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 50/100 (quality, fit, speed and memory use) sets the ranking. | 42.8 tok/s | Runs great | 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 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. | 61.7 tok/s | Runs great | 8Basic quality (D) · 8 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. | 155 tok/s | Runs great |
| SmolLM2 360M Instruct | 8Basic quality (D) · 8 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. | 42.7 tok/s | Runs great | 8Basic quality (D) · 8 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. | 232 tok/s | Runs great |
| Qwen2.5-Math 1.5B Instruct | 19Basic quality (D) · 19 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. | 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 58/100 (quality, fit, speed and memory use) sets the ranking. | 54.3 tok/s | Runs great |
| Qwen1.5 7B Chat | 21Basic quality (D) · 21 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 | Runs well | 21Basic quality (D) · 21 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. | 59.7 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 50/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow | 19Basic quality (D) · 19 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. | 44.9 tok/s | Runs welltight fit |
| Zephyr 7B Beta | 21Basic quality (D) · 21 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. | 11.7 tok/s | Runs well | 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. | 40.7 tok/s | Runs great |
| 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 50/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slow | 23Basic quality (D) · 23 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. | 37.9 tok/s | Runs great |
| Yi 34B Chat | 28Basic quality (D) · 28 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. | 3.1 tok/s | 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. | 3.4 tok/s | Slowheavy RAM offload |
| d1 2B | 17Basic quality (D) · 17 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. | 44.1 tok/s | Runs great | 21Basic quality (D) · 21 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. | 43.5 tok/s | Runs great |
| Gemma 1.1 7B IT | 19Basic quality (D) · 19 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. | 12.6 tok/s | Runs well | 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. | 53.9 tok/s | Runs welltight fit |
| StarCoder2 15B Instruct | 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. | 4.1 tok/s | Slow | 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. | 36.7 tok/s | Runs great |
| CodeGeeX4 All 9B | 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. | 11.4 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. | 37.9 tok/s | Runs great |
| ERNIE 4.5 0.3B | 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. | 42.7 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. | 232 tok/s | Runs great |
| InternLM2 Math Plus 20B | 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. | 3.3 tok/s | Slow | 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. | 23.1 tok/s | Runs welloffloads to RAM |
| 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. | 59.1 tok/s | Runs great | 6Basic quality (D) · 6 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. | 322 tok/s | Runs great |
| TinyLlama 1.1B Chat | 5Basic quality (D) · 5 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 41.3 tok/s | Runs great | 6Basic quality (D) · 6 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. | 76.0 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. | 68.0 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. | 171 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. | 56.9 tok/s | Runs great | 6Basic quality (D) · 6 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. | 310 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 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow | 18Basic quality (D) · 18 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. | 44.9 tok/s | Runs welltight fit |
| 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 49/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow | 18Basic quality (D) · 18 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. | 41.7 tok/s | Runs welloffloads to RAM |
| SmolLM 360M Instruct | 5Basic quality (D) · 5 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. | 42.7 tok/s | Runs great | 5Basic quality (D) · 5 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. | 232 tok/s | Runs great |
| Gemma 7B IT | 18Basic quality (D) · 18 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. | 12.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 53.9 tok/s | Runs welltight fit |
| Orca 2 7B | 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. | 12.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 43.7 tok/s | Runs great |
| Yi Coder 1.5B Chat | 15Basic quality (D) · 15 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. | 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 56.5 tok/s | Runs great |
| Codestral Mamba 7B | 30Basic quality (D) · 30 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. | 11.6 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. | 40.4 tok/s | Runs great |
| DeepSeek Coder 6.7B Instruct | 28Basic quality (D) · 28 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. | 12.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs welltight fit |
| Qwen2.5-Math 7B Instruct | 30Basic quality (D) · 30 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. | 11.1 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. | 38.6 tok/s | Runs great |
| 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. | 118 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. | 643 tok/s | Runs great |
| surya ocr 2.5 | 15Basic quality (D) · 15 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 48.3 tok/s | Runs great | 15Basic quality (D) · 15 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. | 121 tok/s | Runs great |
| Yi 6B Chat | 16Basic quality (D) · 16 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. | 14.0 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. | 40.8 tok/s | Runs great |
| Llama 2 7B Chat | 16Basic quality (D) · 16 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. | 12.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 43.7 tok/s | Runs great |
| Mathstral 7B | 28Basic quality (D) · 28 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. | 11.7 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 40.6 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. | 171 tok/s | Runs great | 3Basic quality (D) · 3 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. | 929 tok/s | Runs great |
| Stable Code Instruct 3B | 14Basic quality (D) · 14 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. | 38.4 tok/s | Runs great | 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. | 64.8 tok/s | Runs great |
| Yi Coder 9B Chat | 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. | 12.2 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 40.4 tok/s | Runs great |
| LLM4Decompile 6.7B V2 | 26Basic quality (D) · 26 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. | 12.6 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 67/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs welltight fit |
| Baichuan 2 7B Chat | 16Basic quality (D) · 16 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. | 11.3 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 47.4 tok/s | Runs great |
| 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. | 118 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. | 643 tok/s | Runs great |
| Granite Code 20B Instruct | 34Basic quality (D) · 34 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. | 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 29.2 tok/s | Runs welltight fit |
| 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 47/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow | 15Basic quality (D) · 15 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. | 44.9 tok/s | Runs welltight fit |
| 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 47/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 tok/s | Slow | 15Basic quality (D) · 15 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. | 43.8 tok/s | Runs welltight fit |
| LLM4Decompile 9B V2 | 26Basic quality (D) · 26 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. | 12.2 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 40.4 tok/s | Runs great |
| DeepSeek LLM 7B Chat | 15Basic quality (D) · 15 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. | 12.2 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 67/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great |
| SQLCoder 7B v2 | 25Basic quality (D) · 25 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. | 12.6 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 52.9 tok/s | Runs welltight fit |
| DeepSeek Coder 1.3B Instruct | 11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 40.0 tok/s | Runs great | 12Basic quality (D) · 12 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. | 61.9 tok/s | Runs great |
| LLM4Decompile 1.3B V2 | 11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 40.0 tok/s | Runs great | 12Basic quality (D) · 12 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. | 61.9 tok/s | Runs great |
| InternLM2 Math Plus 7B | 26Basic quality (D) · 26 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. | 10.9 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. | 46.0 tok/s | Runs great |
| Granite Code 8B Instruct (128K) | 26Basic quality (D) · 26 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. | 10.5 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 44.3 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow | 14Basic quality (D) · 14 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. | 44.9 tok/s | Runs welltight fit |
| StarCoder2 3B | 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. | 35.5 tok/s | Runs great | 18Basic quality (D) · 18 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. | 59.9 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 30.9 tok/s | Runs great | 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. | 52.1 tok/s | Runs great |
| CodeGemma 7B | 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. | 12.6 tok/s | Runs well | 28Basic quality (D) · 28 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. | 53.9 tok/s | Runs welltight fit |
| LLaVA 1.5 7B | 11Basic quality (D) · 11 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. | 15.2 tok/s | Runs well | 15Basic quality (D) · 15 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. | 41.7 tok/s | Runs great |
| DeepSeek Coder 33B Instruct | 30Basic quality (D) · 30 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. | 3.2 tok/s | Slow | 41Fair quality (C) · 41 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. | 3.3 tok/s | Slowheavy RAM offload |
| 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking. | 8.0 tok/s | Slowheavy RAM offload |
| CodeGemma 2B | 9Basic quality (D) · 9 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. | 42.8 tok/s | Runs great | 14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 72.3 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | Slow | 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. | 36.7 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 15.9 tok/s | Runs well | 13Basic quality (D) · 13 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. | 43.7 tok/s | Runs great |
| OLMo 7B Instruct | 9Basic quality (D) · 9 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. | 15.6 tok/s | Runs well | 13Basic quality (D) · 13 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. | 42.7 tok/s | Runs great |
| 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. | 68.0 tok/s | Runs great | 8Basic quality (D) · 8 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. | 171 tok/s | Runs great |
| WizardMath 7B v1.1 | 21Basic quality (D) · 21 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. | 11.7 tok/s | Runs well | 25Basic quality (D) · 25 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. | 40.7 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 45/100 (quality, fit, speed and memory use) sets the ranking. | 14.7 tok/s | Runs well | 11Basic quality (D) · 11 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. | 40.2 tok/s | Runs great |
| Code Llama 7B Instruct | 20Basic quality (D) · 20 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. | 12.6 tok/s | Runs well | 22Basic quality (D) · 22 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. | 52.9 tok/s | Runs welltight fit |
| Granite Code 34B Instruct | 28Basic quality (D) · 28 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. | 3.2 tok/s | 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. | 3.6 tok/s | Slowheavy RAM offload |
| Code Llama 34B Instruct | 26Basic quality (D) · 26 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. | 3.2 tok/s | 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. | 3.3 tok/s | Slowheavy RAM offload |
| StarCoder2 7B | 20Basic quality (D) · 20 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. | 11.8 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. | 41.1 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 44/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 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. | 3.8 tok/s | Slowheavy RAM offload |
| StarCoder 15B | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 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. | 37.0 tok/s | Runs great |
| Falcon 7B Instruct | 4Basic quality (D) · 4 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. | 14.9 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. | 40.8 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 |
| DeepSeek V4.1 Flash 1017 (552B-A16B) | 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 |
| GLM-5.3 (753B-A40B) | 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 |
| 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 |
| 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 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 |
| 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 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 |
| 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 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 V4.1 Flash (552B-A16B) | 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 |
| 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 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 |
| GLM-5.2 (753B-A40B) | 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 |
| Hunyuan Hy4 Preview (780B) | 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 |
| Muse Spark Open (816B-A42B) | 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 (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 |
| Kimi K2.6 (1T) | 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 | 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 |
| 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 9/100 (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 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| 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 9/100 (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 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run |
| GLM-5.1 (744B-A40B) | 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 |
| 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 |
| GLM-5 (744B-A40B) | 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 |
| Kimi K2.5 (1T) | 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 |
| 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 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 |
| DeepSeek V3.2 (671B) | 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 | 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 |
| Inkling (975B-A41B) | 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 | 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 | 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 | 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) | 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 | 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 |
| Kimi K2 Thinking (1T) | 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 | 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 | 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 | 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 |
| Ling 2.6 1T | 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 | 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 |
| DeepSeek R1 (671B) | 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 | 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 |
| DeepSeek V3.1 Terminus | 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 | 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 |
| DeepSeek V3.1 (671B) | 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 | 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 |
| 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 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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 |
| Ling 1T | 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 | 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 |
| Mistral Large 3 (675B) | 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 | 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 |
| 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 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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 |
| LongCat Flash Chat (560B) | 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 | 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 0324 (671B) | 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 | 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 |
| DeepSeek V3 (671B) | 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 | 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 |
Image models
60 of 60 image models run on the Intel Xeon W-2100 series NAS (256 GB). 230 GB usable for models.
52 of 60 image models run on the Intel Arc B570. 10.0 GB usable for models.
| Model | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS | QualityArc B570 | SpeedArc B570 | RunsArc B570 |
|---|---|---|---|---|---|---|
| HunyuanImage 3.0 (80B-A13B) | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 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 80/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 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 79/100 (quality, fit, speed and memory use) sets the ranking. | 35.0 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 |
| Ideogram 4 | 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. | 24.3 min | Very slow | 90Excellent quality (A+) · 90 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. | 2.3 min | Very slowtight fit · CPU offload |
| Krea 2 Turbo | 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. | 4.2 min | Very slow | 90Excellent quality (A+) · 90 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. | 24 s | Runs wellCPU offload |
| Qwen-Image 2.1 | 93Excellent quality (A+) · 93 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. | 58.3 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 |
| Qwen-Image 2512 | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 87.5 min | 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 | 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. | 87.5 min | 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 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 |
| Qwen-Image 2.1 Turbo | 89Excellent quality (A+) · 89 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. | 11.3 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 min | Slow | 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs greatencoder in RAM |
| FireRed-Image-Edit 1.1 | 87Excellent quality (A+) · 87 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. | 77.7 min | Very slow | 80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 9.8 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 21.9 min | Very slow | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 2.3 min | Very slowCPU offload |
| FLUX 3 Image Klein | 91Excellent quality (A+) · 91 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. | 5.5 min | Very slow | 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 25 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 77.7 min | Very slow | 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 9.8 min | Very slowCPU offload |
| HiDream-I1 Full | 84Great quality (A) · 84 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. | 43.7 min | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 5.3 min | Very slowtight fit · CPU offload |
| ERNIE-Image Turbo | 85Excellent quality (A+) · 85 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. | 3.1 min | Very slow | 79Great quality (A) · 79 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. | 19 s | Runs wellencoder in RAM |
| ERNIE-Image | 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. | 21.4 min | Very slow | 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 2.2 min | Slowencoder in RAM |
| HiDream-I1 Dev | 80Great quality (A) · 80 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. | 16.5 min | Very slow | 78Great quality (A) · 78 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. | 1.6 min | Slowtight fit · CPU offload |
| FLUX.2 [klein] 4B | 78Great quality (A) · 78 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. | 58 s | Slow | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 5.6 s | Runs welltight fit |
| HiDream-I1 Fast | 76Great quality (A) · 76 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. | 9.7 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. | 55 s | Slowtight fit · CPU offload |
| Z-Image Turbo | 82Great quality (A) · 82 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. | 2.2 min | Slow | 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs welltight fit · encoder in RAM |
| FLUX.1 Krea [dev] | 82Great quality (A) · 82 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. | 11.7 min | Very slow | 80Great quality (A) · 80 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. | 66 s | SlowCPU offload |
| FLUX.1 Kontext [dev] | 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. | 21.4 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. | 2.0 min | SlowCPU offload |
| MOSS-Image SFT | 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. | 13.6 min | Very slow | 80Great quality (A) · 80 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. | 62 s | Slowencoder in RAM |
| FLUX.1 [dev] | 80Great quality (A) · 80 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. | 11.7 min | Very slow | 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 65 s | Slowtight fit · encoder in RAM |
| Z-Image | 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. | 16.5 min | Very slow | 80Great quality (A) · 80 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. | 75 s | 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 min | Very slow | 74Great quality (A) · 74 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. | 69 s | SlowCPU offload |
| FLUX.1 [schnell] | 70Great quality (A) · 70 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. | 1.9 min | Slow | 65Good quality (B) · 65 of 100: how capable the model is at NF4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs welltight fit · encoder in RAM |
| Chroma1-HD | 78Great quality (A) · 78 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. | 19.4 min | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at NF4, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 min | Slowencoder in RAM |
| CogView4 6B | 70Great quality (A) · 70 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. | 17.5 min | Very slow | 68Good quality (B) · 68 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. | 80 s | Slowtight fit · encoder in RAM |
| 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 min | Slow | 57Good quality (B) · 57 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 9.5 s | Runs greatencoder in RAM |
| Iris-3B | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 15.5 min | Very slow | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 79 s | Slowencoder 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 10.7 min | Very slow | 61Good quality (B) · 61 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 65 s | Slowencoder in RAM |
| SDXL Turbo | 40Fair quality (C) · 40 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. | 8.7 s | Runs great | 40Fair quality (C) · 40 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. | 0.7 s | Runs great |
| OmniGen2 | 66Good quality (B) · 66 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. | 15.5 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. | 71 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 76 s | Slow | 56Good quality (B) · 56 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. | 5.5 s | Runs great |
| SDXL-Lightning (4-step) | 52Fair quality (C) · 52 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. | 37 s | Runs well | 52Fair quality (C) · 52 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. | 3.0 s | Runs great |
| Kolors | 60Good quality (B) · 60 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. | 3.9 min | Very slow | 58Good quality (B) · 58 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. | 18 s | Runs wellencoder in RAM |
| Juggernaut XL v9 | 62Good quality (B) · 62 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. | 4.4 min | Very slow | 60Good quality (B) · 60 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. | 19 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 56/100 (quality, fit, speed and memory use) sets the ranking. | 4.4 min | Very slow | 60Good quality (B) · 60 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. | 19 s | Runs well |
| Lumina-Image 2.0 | 62Good quality (B) · 62 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. | 6.8 min | Very slow | 60Good quality (B) · 60 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. | 30 s | Runs well |
| 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. | 4.1 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. | 18 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. | 4.1 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. | 18 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 55/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 min | Very slow | 58Good quality (B) · 58 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. | 30 s | Runs wellencoder in RAM |
| Pony Diffusion V6 XL | 58Good quality (B) · 58 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. | 3.7 min | Very slow | 56Good quality (B) · 56 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. | 16 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 55/100 (quality, fit, speed and memory use) sets the ranking. | 7.3 min | Very slow | 58Good quality (B) · 58 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. | 32 s | Runs well |
| AuraFlow v0.3 | 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. | 13.6 min | Very slow | 53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 79 s | Slow |
| Animagine XL 3.1 | 56Good quality (B) · 56 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. | 4.1 min | Very slow | 54Fair quality (C) · 54 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well |
| PixArt-Σ XL 1024 | 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. | 87 s | Slow | 50Fair quality (C) · 50 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. | 7.4 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 min | Very slow | 50Fair quality (C) · 50 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. | 14 s | Runs wellencoder in RAM |
| Stable Diffusion XL 1.0 | 55Good quality (B) · 55 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. | 4.4 min | Very slow | 53Fair quality (C) · 53 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. | 19 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. | 4.7 s | Runs great | 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 s | Runs great |
| Stable Cascade | 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. | 4.9 min | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 21 s | Runs well |
| 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. | 5.8 min | Very slow | 52Fair quality (C) · 52 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. | 28 s | Runs welltight fit |
| Kandinsky 3 | 48Fair quality (C) · 48 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. | 8.7 min | Very slow | 48Fair quality (C) · 48 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. | 44 s | Slowtight fit · encoder in RAM |
| LCM DreamShaper v7 | 30Basic quality (D) · 30 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. | 15 s | Runs well | 30Basic quality (D) · 30 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. | 1.2 s | Runs great |
| 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. | 70 s | Slow | 42Fair quality (C) · 42 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. | 5.6 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. | 70 s | Slow | 40Fair quality (C) · 40 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. | 5.6 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 46/100 (quality, fit, speed and memory use) sets the ranking. | 70 s | Slow | 35Basic quality (D) · 35 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. | 5.6 s | Runs great |
Video models
43 of 43 video models run on the Intel Xeon W-2100 series NAS (256 GB). 230 GB usable for models.
11 of 43 video models run on the Intel Arc B570. 10.0 GB usable for models.
| Model | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS | QualityArc B570 | SpeedArc B570 | RunsArc B570 |
|---|---|---|---|---|---|---|
| Cosmos3-Super Image2Video (64B) | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 36.4 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 16.8 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 |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 88.4 min | 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 47.6 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 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 |
| Wan 2.2 I2V A14B | 86Excellent quality (A+) · 86 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. | 25.9 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 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 |
| HunyuanVideo 1.5 (8.3B) | 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. | 29.2 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 |
| 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 68/100 (quality, fit, speed and memory use) sets the ranking. | 11.7 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 |
| Step-Video T2V (30B) | 76Great quality (A) · 76 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. | 50.2 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 67/100 (quality, fit, speed and memory use) sets the ranking. | 71.3 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 2.2 Animate 14B | 78Great quality (A) · 78 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. | 30.8 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 67/100 (quality, fit, speed and memory use) sets the ranking. | 35.6 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 |
| SCAIL-2 14B (character animation) | 80Great quality (A) · 80 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. | 19.4 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 |
| SkyReels V2 T2V 14B 720P | 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. | 38.9 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 32.4 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 66/100 (quality, fit, speed and memory use) sets the ranking. | 32.4 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 2.2 S2V 14B (speech to video) | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 16.2 h | Very slow | 70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 h | Very slowtight fit · CPU offload |
| FramePack I2V (HunyuanVideo 13B) | 74Great quality (A) · 74 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. | 6.5 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 |
| 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 8.6 h | 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. | 48.5 min | Very slowCPU offload |
| HunyuanVideo 13B | 72Great quality (A) · 72 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. | 38.9 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 64/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 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 |
| SkyReels V2 T2V 14B 540P | 74Great quality (A) · 74 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. | 22.7 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 h | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 h | Very slowtight fit · CPU offload |
| 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 63/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 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 62/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 8.4 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 61/100 (quality, fit, speed and memory use) sets the ranking. | 48.6 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 60/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 h | Very slow | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 31.5 min | Slowtight fit · CPU offload |
| 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 8.9 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 57/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 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 |
| Mochi 1 Preview (10B) | 62Good quality (B) · 62 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. | 17.8 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-Predict2 2B Video2World | 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. | 4.0 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 54/100 (quality, fit, speed and memory use) sets the ranking. | 24.3 min | Slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 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 54/100 (quality, fit, speed and memory use) sets the ranking. | 2.9 h | Very slow | 55Good quality (B) · 55 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. | 18.3 min | SlowCPU offload |
| CogVideoX 5B | 55Good quality (B) · 55 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. | 2.9 h | Very slow | 53Fair quality (C) · 53 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. | 13.3 min | Slowtight fit · encoder in RAM |
| 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 h | Very slow | 53Fair quality (C) · 53 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. | 19.2 min | Slowencoder in RAM |
| 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 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 h | Very slow | 55Good quality (B) · 55 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. | 19.7 min | Slowencoder in RAM |
| Allegro (2.8B) | 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. | 19.4 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 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.9 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 50/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 min | Very slow | 44Fair quality (C) · 44 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. | 4.4 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 47/100 (quality, fit, speed and memory use) sets the ranking. | 19.4 min | Slow | 35Basic quality (D) · 35 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. | 1.6 min | Runs great |
Decision models
70 of 70 decision models run on the Intel Xeon W-2100 series NAS (256 GB). 230 GB usable for models.
66 of 70 decision models run on the Intel Arc B570. 10.0 GB usable for models.
| Model | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS | QualityArc B570 | SpeedArc B570 | RunsArc B570 |
|---|---|---|---|---|---|---|
| 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. | 48 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. | 5.3 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. | 114 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. | 7.6 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. | 875 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. | 35 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. | 383 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. | 875 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. | 35 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. | 5.8 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. | 189 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. | 638 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. | 25 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. | 151 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. | 8.8 ms | Runs great |
| 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. | 11.9 s | Very slow | 89Excellent quality (A+) · 89 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. | 369 ms | Runs well |
| 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. | 313 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. | 14 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. | 5.8 s | Very slow | 88Excellent quality (A+) · 88 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. | 189 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. | 23.2 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. | 437 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. | 18 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. | 143 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. | 8.6 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. | 236 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. | 12 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 81/100 (quality, fit, speed and memory use) sets the ranking. | 875 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. | 35 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. | 5.6 s | Very slow | 86Excellent quality (A+) · 86 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. | 181 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. | 344 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. | 15 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. | 3.4 s | Very slow | 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 114 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. | 236 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. | 12 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. | 166 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. | 9.3 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. | 2.2 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. | 85 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 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 Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 84 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. | 313 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. | 14 ms | Runs great |
| 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. | 716 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. | 30 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. | 20.2 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 |
| 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. | 2.5 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. | 94 ms | Runs great |
| 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. | 329 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. | 15 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. | 329 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. | 15 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. | 23.4 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 |
| 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. | 437 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. | 18 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. | 282 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 |
| 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. | 3.5 s | Very slow | 80Great quality (A) · 80 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. | 104 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. | 45 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. | 5.2 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. | 761 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. | 29 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. | 3.6 s | Very slow | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 119 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. | 885 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. | 33 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 13.1 s | Very slow | 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. | 534 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. | 7.1 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. | 290 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. | 251 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. | 12.9 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. | 524 ms | Slow |
| 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. | 13.4 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. | 547 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. | 344 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. | 15 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. | 65 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. | 228 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. | 1.2 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. | 88 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. | 11.6 s | Very slow | 79Great quality (A) · 79 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. | 473 ms | Slow |
| 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. | 13.1 s | Very slow | 79Great quality (A) · 79 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. | 533 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. | 5.4 s | Very slow | 73Great quality (A) · 73 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. | 386 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. | 321 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 240.7 s | Very slow | 85Excellent quality (A+) · 85 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. | 70.9 s | Very slowheavy RAM offload |
| NuExtract 2.0 2B | 70Great quality (A) · 70 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. | 3.2 s | Very slow | 66Good quality (B) · 66 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. | 198 ms | Runs well |
| gpt-oss-safeguard 120B | 80Great quality (A) · 80 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. | 19.4 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 |
| 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. | 1.2 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. | 44 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. | 51.0 s | Very slow | 78Great quality (A) · 78 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. | 5.6 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 26.8 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. | 3.0 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. | 59.0 s | Very slow | 79Great quality (A) · 79 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. | 5.5 s | Very slow |
| 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. | 13.9 s | Very slow | 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 s | Very slowoffloads to RAM |
| 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. | 39.5 s | Very slow | 66Good quality (B) · 66 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. | 2.7 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. | 13.4 s | Very slow | 62Good quality (B) · 62 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. | 409 ms | Slow |
| 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. | 56.0 s | Very slow | 77Great quality (A) · 77 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. | 5.2 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. | 12.9 s | Very slow | 67Good quality (B) · 67 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. | 524 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. | 3.8 s | Very slow | 58Good quality (B) · 58 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. | 124 ms | Runs great |
| 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. | 12.6 s | Very slow | 67Good quality (B) · 67 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. | 1.2 s | Slow |
| 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. | 95.3 s | Very slow | 70Great quality (A) · 70 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. | 20.7 s | Very slowheavy RAM offload |
| 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. | 19.2 s | Very slow | 62Good quality (B) · 62 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. | 692 ms | Slowtight fit |
| 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. | 2.4 s | Very slow | 55Good quality (B) · 55 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. | 101 ms | Runs great |
| 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. | 53.2 s | Very slow | 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. | 5.0 s | Very slow |
| 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. | 28.1 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. | 2.6 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. | 28.1 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. | 2.6 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.