NVIDIA GeForce RTX 4090 vs Intel Xeon W-2100 series NAS (512 GB) 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 (512 GB)
For general chat: It runs 119 more LLMs (614 vs 495). On the other hand, the NVIDIA GeForce RTX 4090 is about 28.3× faster on its own top models.
 NVIDIA GeForce RTX 4090
|
 Intel Xeon W-2100 series NAS (512 GB)
|
|
|---|---|---|
| Memory | 24.0 GB VRAM | 512 GB unified |
| Usable for models | 24.0 GB | 471 GB |
| Memory bandwidth | 1,008 GB/s | 85 GB/s |
| FP16 compute | 82.6 TFLOPS | 0.8 TFLOPS |
| Launch price | $1,599 | — |
| Released | 2022 | 2017 |
| LLMs that run | 495 of 619 | 614 of 619 |
| LLMs that run well | 465 | 366 |
| Image models that run | 57 of 60 | 60 of 60 |
| Video models that run | 31 of 43 | 43 of 43 |
| Decision models that run | 68 of 70 | 70 of 70 |
| Top-10 LLM average score | 99 | 90 |
| Top-10 LLM average speed | 89.3 tok/s | 3.2 tok/s |
| Best LLM | Qwen3.8 27B | Intern-S2 (397B-A17B) |
Highlighted values are the best of the two. Model results assume 8K of context and the default macOS GPU memory limit on Macs.
LLMs
495 of 619 LLMs run on the NVIDIA GeForce RTX 4090. 24.0 GB usable for models.
614 of 619 LLMs run on the Intel Xeon W-2100 series NAS (512 GB). 471 GB usable for models.
| Model | QualityRTX 4090 | SpeedRTX 4090 | RunsRTX 4090 | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS |
|---|---|---|---|---|---|---|
| Qwen3.8 27B | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. | 36.8 tok/s | Runs welltight fit | 80Great quality (A) · 80 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 |
| Qwen3.6 27B | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great | 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 |
| Gemma 4 26B-A4B | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. | 124 tok/s | Runs welltight fit | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 11.5 tok/s | Runs well |
| Qwen3.5 27B | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. | 44.5 tok/s | Runs great | 78Great quality (A) · 78 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. | 3.0 tok/s | Slow |
| Nanbeige4.3 33B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. | 37.4 tok/s | Runs welltight fit | 66Good quality (B) · 66 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. | 3.2 tok/s | Slow |
| Muse Glimmer 30B | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 99/100 (quality, fit, speed and memory use) sets the ranking. | 41.6 tok/s | Runs great | 64Good quality (B) · 64 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. | 3.6 tok/s | Slow |
| 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 98/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 88Excellent quality (A+) · 88 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 |
| 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 98/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 88Excellent quality (A+) · 88 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 |
| 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 98/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 88Excellent quality (A+) · 88 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 |
| TMax 27B | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. | 45.2 tok/s | Runs great | 75Great quality (A) · 75 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 |
| 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 98/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 87Excellent quality (A+) · 87 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 |
| 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 97/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 86Excellent quality (A+) · 86 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 |
| Gemma 4 31B | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. | 39.6 tok/s | Runs welltight fit | 63Good quality (B) · 63 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. | 3.4 tok/s | Slow |
| Fara 1.5 27B | 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. | 45.2 tok/s | Runs great | 73Great quality (A) · 73 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 |
| Raon-1 mini Preview (30B-A4B) | 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. | 146 tok/s | Runs great | 87Excellent quality (A+) · 87 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. | 10.2 tok/s | Runs well |
| 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 97/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well |
| 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 97/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 84Great quality (A) · 84 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 |
| 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 97/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 84Great quality (A) · 84 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 |
| Gemma 4 12B | 83Great quality (A) · 83 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | 52.7 tok/s | Runs great | 82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow |
| UI-Mate 27B | 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | 45.2 tok/s | Runs great | 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 |
| 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 96/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 83Great quality (A) · 83 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 |
| 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 96/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 82Great quality (A) · 82 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. | 20.3 tok/s | Runs well |
| 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 96/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 82Great quality (A) · 82 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. | 20.3 tok/s | Runs well |
| 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 94/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 77Great quality (A) · 77 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 |
| DiffusionGemma 26B-A4B IT | 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 121 tok/s | Runs welltight fit | 74Great quality (A) · 74 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. | 15.5 tok/s | Runs well |
| EXAONE 4.5 33B | 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 36.0 tok/s | Runs welltight fit | 57Good quality (B) · 57 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. | 3.1 tok/s | Slow |
| 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 93/100 (quality, fit, speed and memory use) sets the ranking. | 161 tok/s | Runs welltight fit | 76Great quality (A) · 76 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 |
| Devstral Small 2 (24B) | 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 3.5 tok/s | Slow |
| K2 Horizon 7B | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 70.0 tok/s | Runs great | 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 |
| Flint (40B-A2.5B) | 75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | 208 tok/s | Runs welltight fit | 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. | 24.1 tok/s | Runs well |
| 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 92/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 86Excellent quality (A+) · 86 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 |
| Apriel 1.5 15B Thinker | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 42.4 tok/s | Runs great | 71Great quality (A) · 71 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. | 3.1 tok/s | Slow |
| LFM2.5 24B-A2B | 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 170 tok/s | Runs great | 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. | 24.5 tok/s | Runs well |
| SenseNova Loop 9B Preview | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 65.2 tok/s | Runs great | 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 |
| 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 161 tok/s | Runs welltight fit | 73Great quality (A) · 73 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. | 17.6 tok/s | Runs well |
| 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs welltight fit | 73Great quality (A) · 73 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 |
| Nemotron 3.5 Bolt E4B | 70Great quality (A) · 70 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. | 64.5 tok/s | Runs great | 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 |
| Phi-4 Reasoning Vision 15B | 70Great quality (A) · 70 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. | 41.7 tok/s | Runs great | 69Good quality (B) · 69 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. | 3.0 tok/s | Slow |
| Granite 4.2 30B | 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. | 42.3 tok/s | Runs welltight fit | 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 |
| 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 91/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs welltight fit | 72Great quality (A) · 72 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 |
| Ornith 1.5 9B | 77Great quality (A) · 77 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. | 65.3 tok/s | Runs great | 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 |
| Hunyuan Hy-Memory 30B-A3B | 82Great quality (A) · 82 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | 155 tok/s | Runs welltight fit | 80Great quality (A) · 80 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. | 20.3 tok/s | Runs well |
| Qwen3 32B | 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. | 37.7 tok/s | Runs welltight fit | 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Qwen3.5 9B | 76Great quality (A) · 76 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. | 65.3 tok/s | Runs great | 53Fair quality (C) · 53 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 |
| Gemma 3 27B IT | 68Good quality (B) · 68 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. | 45.2 tok/s | Runs great | 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Qwen3 30B-A3B | 70Great quality (A) · 70 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. | 166 tok/s | Runs welltight fit | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 tok/s | Runs well |
| 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 90/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs welltight fit | 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 tok/s | Runs well |
| Gemma 4 E4B | 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 64.5 tok/s | Runs great | 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 |
| Qwen3 14B | 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. | 42.6 tok/s | Runs great | 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. | 3.1 tok/s | Slow |
| Ornith 1.0 9B | 75Great quality (A) · 75 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. | 65.3 tok/s | Runs great | 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 |
| Devstral Small 1.1 (24B) | 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 tok/s | Runs great | 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. | 3.6 tok/s | Slow |
| Magistral Small 2507 | 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 tok/s | Runs great | 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. | 3.6 tok/s | Slow |
| GLM-4 32B 0414 | 70Great quality (A) · 70 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. | 38.0 tok/s | Runs welltight fit | 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 |
| MedGemma 27B Text IT | 66Good quality (B) · 66 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. | 45.8 tok/s | Runs great | 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 |
| gpt-oss 20B | 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 164 tok/s | Runs great | 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 |
| Granite 4.1 30B | 68Good quality (B) · 68 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. | 42.9 tok/s | Runs welltight fit | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow |
| 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 89/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 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. | 20.3 tok/s | Runs well |
| Hermes 4 14B | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 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 |
| Magistral Small 2506 | 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 tok/s | Runs great | 57Good quality (B) · 57 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. | 3.6 tok/s | Slow |
| Mistral Small 3.2 24B | 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 57Good quality (B) · 57 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 |
| EXAONE 4.0 32B | 68Good quality (B) · 68 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. | 38.7 tok/s | Runs welltight fit | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow |
| Qwen3-VL 32B Instruct | 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 48.0 tok/s | Runs great | 54Fair quality (C) · 54 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. | 3.2 tok/s | Slow |
| Olmo 3.1 32B Instruct | 68Good quality (B) · 68 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. | 38.4 tok/s | Runs welltight fit | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| TMax 9B | 74Great quality (A) · 74 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. | 70.4 tok/s | Runs great | 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 |
| Seed-OSS 36B Instruct | 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs welltight fit | 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. | 1.3 tok/s | Very slow |
| Terminal RSI 27B | 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. | 44.5 tok/s | Runs great | 57Good quality (B) · 57 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. | 3.0 tok/s | Slow |
| Sarvam 30B | 66Good quality (B) · 66 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. | 189 tok/s | Runs welltight fit | 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. | 25.0 tok/s | Runs well |
| North Mini Code 1.0 (30B-A3B) | 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 155 tok/s | Runs welltight fit | 76Great quality (A) · 76 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 |
| Hermes 4.3 36B | 66Good quality (B) · 66 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 44.2 tok/s | Runs welltight fit | 78Great quality (A) · 78 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. | 1.3 tok/s | Very slow |
| Mistral Small 3.1 24B | 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 55Good quality (B) · 55 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 |
| InternVL3 14B | 64Good quality (B) · 64 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. | 41.7 tok/s | Runs great | 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 |
| Ministral 3 14B | 64Good quality (B) · 64 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. | 45.2 tok/s | Runs great | 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 |
| Phi-4 (14B) | 64Good quality (B) · 64 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. | 42.9 tok/s | Runs great | 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 |
| Hemmingway 1.5 | 63Good quality (B) · 63 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. | 46.0 tok/s | Runs great | 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 |
| ERNIE 4.5 21B-A3B | 63Good quality (B) · 63 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. | 141 tok/s | Runs great | 60Good quality (B) · 60 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. | 20.3 tok/s | Runs well |
| Baichuan M2 32B | 66Good quality (B) · 66 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. | 37.8 tok/s | Runs welltight fit | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Qwen2.5 32B Instruct | 66Good quality (B) · 66 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. | 37.7 tok/s | Runs welltight fit | 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Trinity Mini (26B-A3B) | 65Good quality (B) · 65 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. | 141 tok/s | Runs welltight fit | 62Good quality (B) · 62 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 |
| Mistral Small 3 24B (2501) | 62Good quality (B) · 62 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 tok/s | Runs great | 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 |
| Qwen2.5 14B Instruct | 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. | 42.9 tok/s | Runs great | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| InternVL3.5 38B | 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 41.7 tok/s | Runs welltight fit | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Granite 4.2 8B | 68Good quality (B) · 68 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. | 71.7 tok/s | Runs great | 47Fair quality (C) · 47 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. | 12.2 tok/s | Runs well |
| Phi-4 Reasoning Plus (14B) | 72Great quality (A) · 72 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. | 43.0 tok/s | Runs great | 71Great quality (A) · 71 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 |
| 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 87/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs welltight fit | 74Great quality (A) · 74 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. | 18.6 tok/s | Runs well |
| 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 87/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs welltight fit | 74Great quality (A) · 74 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. | 18.6 tok/s | Runs well |
| Dolphin Mistral 24B Venice Edition | 60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 52Fair quality (C) · 52 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. | 3.5 tok/s | Slow |
| Voxtral Small 24B | 60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 42.1 tok/s | Runs great | 52Fair quality (C) · 52 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. | 3.5 tok/s | Slow |
| Kimi-VL A3B Thinking 2506 | 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs great | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well |
| Ling 3.0 Tiny (8B-A1.3B) | 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 113 tok/s | Runs great | 57Good quality (B) · 57 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. | 43.0 tok/s | Runs great |
| Qwen2.5 14B Instruct 1M | 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| QwQ 32B | 74Great quality (A) · 74 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. | 37.8 tok/s | Runs welltight fit | 54Fair quality (C) · 54 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 |
| Gemma 3 12B IT | 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. | 51.6 tok/s | Runs great | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow |
| Nanbeige4.2 3B | 68Good quality (B) · 68 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. | 69.6 tok/s | Runs great | 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 |
| MiMo V2.6 Distill Qwen 9B | 78Great quality (A) · 78 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. | 66.9 tok/s | Runs great | 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 |
| Gemma 2 27B IT | 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. | 45.5 tok/s | Runs great | 52Fair quality (C) · 52 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. | 3.1 tok/s | Slow |
| Phi-4 Reasoning (14B) | 70Great quality (A) · 70 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. | 43.0 tok/s | Runs great | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Qwen3-Omni 30B-A3B Instruct | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 189 tok/s | Runs great | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 18.6 tok/s | Runs well |
| Magistral Small 1.2 (24B) | 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 42.6 tok/s | Runs great | 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 |
| Dolphin 3.0 R1 Mistral 24B | 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 43.4 tok/s | Runs great | 50Fair quality (C) · 50 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. | 3.6 tok/s | Slow |
| Solar Pro Preview 22B | 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 46.2 tok/s | Runs great | 50Fair quality (C) · 50 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. | 3.8 tok/s | Slow |
| Olmo 3.1 32B Think | 72Great quality (A) · 72 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. | 38.4 tok/s | Runs welltight fit | 53Fair quality (C) · 53 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 |
| ERNIE 4.5 21B-A3B Thinking | 69Good quality (B) · 69 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. | 141 tok/s | Runs great | 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 |
| Maple Preview (20B-A1B) | 69Good quality (B) · 69 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. | 187 tok/s | Runs great | 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 |
| OpenReasoning Nemotron 32B | 72Great quality (A) · 72 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. | 37.8 tok/s | Runs welltight fit | 53Fair quality (C) · 53 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 |
| Skywork OR1 32B | 72Great quality (A) · 72 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. | 37.8 tok/s | Runs welltight fit | 53Fair quality (C) · 53 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 |
| Falcon-H1 34B Instruct | 60Good quality (B) · 60 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. | 36.8 tok/s | Runs welltight fit | 44Fair quality (C) · 44 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 |
| Mellum2.1 Thinking (12B-A2.5B) | 70Great quality (A) · 70 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. | 129 tok/s | Runs great | 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. | 24.1 tok/s | Runs well |
| Qwen2.5-VL 32B Instruct | 57Good quality (B) · 57 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. | 47.8 tok/s | Runs great | 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow |
| 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 85/100 (quality, fit, speed and memory use) sets the ranking. | 173 tok/s | Runs welltight fit | 58Good quality (B) · 58 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. | 20.3 tok/s | Runs well |
| Granite 4.0 H Small (32B-A9B) | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 94.0 tok/s | Runs welltight fit | 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 |
| InternVL3 38B | 58Good quality (B) · 58 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. | 41.7 tok/s | Runs welltight fit | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Nemotron Labs Dory 1.0 4B | 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. | 72.9 tok/s | Runs great | 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 |
| Groot 19B A3B 261023 | 56Good quality (B) · 56 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. | 141 tok/s | Runs great | 54Fair quality (C) · 54 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well |
| EXAONE Deep 32B | 70Great quality (A) · 70 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. | 38.7 tok/s | Runs welltight fit | 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. | 3.4 tok/s | Slow |
| GLM-Z1 32B (0414) | 70Great quality (A) · 70 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. | 38.0 tok/s | Runs welltight fit | 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 |
| Command R (08-2024) 32B | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 38.3 tok/s | Runs welltight fit | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Qwen3-VL 8B Instruct | 62Good quality (B) · 62 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. | 71.8 tok/s | Runs great | 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well |
| AceReason Nemotron 14B | 66Good quality (B) · 66 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. | 42.6 tok/s | Runs great | 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 |
| Apriel Nemotron 15B Thinker | 66Good quality (B) · 66 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. | 42.1 tok/s | Runs great | 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 |
| Ministral 3 14B Reasoning | 66Good quality (B) · 66 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. | 45.2 tok/s | Runs great | 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 |
| OpenReasoning Nemotron 14B | 66Good quality (B) · 66 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. | 42.6 tok/s | Runs great | 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 |
| Qwen2.5 Coder 14B Instruct | 66Good quality (B) · 66 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. | 42.6 tok/s | Runs great | 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 |
| Spark-X2.6 4B | 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. | 70.6 tok/s | Runs great | 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 |
| Gemma 4 E2B | 62Good quality (B) · 62 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. | 126 tok/s | Runs great | 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 |
| GLM-4.1V 9B Thinking | 60Good quality (B) · 60 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. | 61.2 tok/s | Runs great | 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 |
| InternVL3.5 8B | 62Good quality (B) · 62 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. | 73.8 tok/s | Runs great | 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 |
| LFM2 24B-A2B | 54Fair quality (C) · 54 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. | 174 tok/s | Runs great | 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 26.0 tok/s | Runs well |
| Reka Flash 3.1 (21B) | 65Good quality (B) · 65 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. | 41.1 tok/s | Runs great | 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| DeepSeek R1 Distill Qwen 32B | 68Good quality (B) · 68 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. | 37.7 tok/s | Runs welltight fit | 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| OLMo 2 32B Instruct | 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. | 38.4 tok/s | Runs welltight fit | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Aya Expanse 32B | 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. | 38.3 tok/s | Runs welltight fit | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| NorthCUA Mini | 56Good quality (B) · 56 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. | 173 tok/s | Runs welltight fit | 56Good quality (B) · 56 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 |
| Aya Vision 32B | 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. | 37.3 tok/s | Runs welltight fit | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slow |
| Granite 4.1 8B | 60Good quality (B) · 60 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. | 71.7 tok/s | Runs great | 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 |
| Qwen3.5 4B | 62Good quality (B) · 62 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. | 62.3 tok/s | Runs great | 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 |
| Devstral Small 2505 | 64Good quality (B) · 64 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. | 43.4 tok/s | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| DeepCoder 14B Preview | 64Good quality (B) · 64 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. | 42.6 tok/s | Runs great | 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 |
| MiniCPM-V 4.5 8B | 60Good quality (B) · 60 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. | 72.4 tok/s | Runs great | 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 |
| Mistral Small 22B (2409) | 52Fair quality (C) · 52 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. | 45.9 tok/s | Runs great | 45Fair quality (C) · 45 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 | Slow |
| OpenHands LM 32B | 66Good quality (B) · 66 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. | 37.8 tok/s | Runs welltight fit | 49Fair quality (C) · 49 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 |
| LFM2.5 8B-A1B | 52Fair quality (C) · 52 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. | 105 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 38.0 tok/s | Runs great |
| Ling Mini 2.0 (16B-A1.4B) | 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 166 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 40.4 tok/s | Runs great |
| Mistral Nemo 12B Instruct | 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 51.6 tok/s | Runs great | 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 |
| Qwen3 8B | 60Good quality (B) · 60 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. | 76.9 tok/s | Runs great | 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 |
| SenseNova 6.8 Code2Video | 62Good quality (B) · 62 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. | 45.2 tok/s | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| UI-Mate 9B | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 66.9 tok/s | Runs great | 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 |
| UI-Venus 2 9B | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 66.9 tok/s | Runs great | 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 |
| Nemotron Nano 9B v2 | 60Good quality (B) · 60 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. | 70.9 tok/s | Runs great | 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 |
| DeepSeek R1 Distill Qwen 14B | 62Good quality (B) · 62 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. | 42.6 tok/s | Runs great | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| JanusCoder 14B | 62Good quality (B) · 62 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. | 42.6 tok/s | Runs great | 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Agents-A1 4B | 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. | 63.9 tok/s | Runs great | 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 |
| TMax 4B | 61Good quality (B) · 61 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. | 69.0 tok/s | Runs great | 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 |
| Kimi-VL A3B Instruct | 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. | 117 tok/s | Runs great | 47Fair quality (C) · 47 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. | 20.3 tok/s | Runs well |
| Pixtral 12B (2409) | 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. | 50.8 tok/s | Runs great | 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 |
| MiMo-VL 7B RL | 58Good quality (B) · 58 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. | 75.8 tok/s | Runs great | 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 |
| Kimi Linear 48B-A3B | 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 217 tok/s | Runs welltight fit | 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. | 20.3 tok/s | Runs well |
| InternLM2.5 20B Chat | 49Fair quality (C) · 49 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. | 43.2 tok/s | Runs great | 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 |
| Qwen2.5 Coder 32B Instruct | 63Good quality (B) · 63 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. | 37.7 tok/s | Runs welltight fit | 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 |
| Mage-VL 4.7B | 56Good quality (B) · 56 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. | 61.2 tok/s | Runs great | 53Fair quality (C) · 53 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. | 13.8 tok/s | Runs well |
| Ministral 3 8B | 56Good quality (B) · 56 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. | 70.6 tok/s | Runs great | 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 12.0 tok/s | Runs well |
| Codestral 22B | 60Good quality (B) · 60 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. | 45.9 tok/s | Runs great | 52Fair quality (C) · 52 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 | Slow |
| Falcon 3 10B Instruct | 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. | 61.1 tok/s | Runs great | 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 |
| Fara 1.5 4B | 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 63.9 tok/s | Runs great | 55Good quality (B) · 55 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. | 14.4 tok/s | Runs well |
| QwQ 32B Preview | 62Good quality (B) · 62 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. | 37.8 tok/s | Runs welltight fit | 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| MiMo 7B RL | 56Good quality (B) · 56 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. | 80.4 tok/s | Runs great | 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 |
| Qwen3-VL 4B Instruct | 54Fair quality (C) · 54 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. | 65.4 tok/s | Runs great | 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 |
| Gemma 3n E4B | 46Fair quality (C) · 46 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. | 72.6 tok/s | Runs great | 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 |
| Moonlight 16B-A3B Instruct | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 117 tok/s | Runs great | 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. | 20.3 tok/s | Runs well |
| Phi-3 Medium (14B) | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 45.1 tok/s | Runs great | 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 |
| Phi-3 Medium 128K Instruct | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 45.1 tok/s | Runs great | 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 |
| InternVL3 8B | 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. | 79.3 tok/s | Runs great | 47Fair quality (C) · 47 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. | 10.7 tok/s | Runs well |
| LLM4Decompile 22B V2 | 56Good quality (B) · 56 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 45.9 tok/s | Runs great | 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 |
| Llama 3.1 Nemotron Nano 8B v1 | 54Fair quality (C) · 54 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. | 78.4 tok/s | Runs great | 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 |
| Gemma 2 9B IT | 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. | 68.2 tok/s | Runs great | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 11.6 tok/s | Runs well |
| 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 80/100 (quality, fit, speed and memory use) sets the ranking. | 136 tok/s | Runs welltight fit | 47Fair quality (C) · 47 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. | 12.3 tok/s | Runs well |
| GLM-4 9B 0414 | 52Fair quality (C) · 52 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. | 67.0 tok/s | Runs great | 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 |
| NorthCUA Nano | 52Fair quality (C) · 52 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. | 66.9 tok/s | Runs great | 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 |
| Qwen3 4B Instruct 2507 | 54Fair quality (C) · 54 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. | 72.2 tok/s | Runs great | 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 |
| Granite 4.0 H Tiny (7B-A1B) | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 128 tok/s | Runs great | 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 |
| OLMo 2 13B Instruct | 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. | 45.9 tok/s | Runs great | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 4.8 tok/s | Slow |
| MiniCPM4 8B | 54Fair quality (C) · 54 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. | 76.9 tok/s | Runs great | 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 |
| Yi 1.5 34B Chat | 47Fair quality (C) · 47 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. | 36.0 tok/s | Runs welltight fit | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| MiniCPM-o 2.6 8B | 52Fair quality (C) · 52 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. | 72.7 tok/s | Runs great | 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. | 12.4 tok/s | Runs well |
| DeepSeek R1 0528 Qwen3 8B | 62Good quality (B) · 62 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. | 76.9 tok/s | Runs great | 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 |
| Qwen2.5-VL 7B Instruct | 52Fair quality (C) · 52 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. | 76.0 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 10.2 tok/s | Runs well |
| Mage-VL-Cowork 4.7B | 60Good quality (B) · 60 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. | 61.2 tok/s | Runs great | 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 |
| MiniCPM5 2B | 60Good quality (B) · 60 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. | 115 tok/s | Runs great | 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 |
| Qwen2.5-Omni 7B | 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. | 58.7 tok/s | Runs great | 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 |
| Hunyuan 7B Instruct | 52Fair quality (C) · 52 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. | 84.0 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well |
| InternLM2 Chat 20B | 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 43.2 tok/s | Runs great | 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| GLM-4 9B Chat 1M | 48Fair quality (C) · 48 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. | 66.4 tok/s | Runs great | 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 |
| InternLM3 8B Instruct | 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 71.6 tok/s | Runs great | 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 |
| InternVL2.5 8B | 50Fair quality (C) · 50 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. | 78.0 tok/s | Runs great | 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 |
| Foundation-Sec 1.1 8B Instruct | 50Fair quality (C) · 50 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. | 78.4 tok/s | Runs great | 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 |
| DeepSeek Coder V2 Lite (16B) | 52Fair quality (C) · 52 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. | 131 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 25.0 tok/s | Runs well |
| Qwen2.5 7B Instruct | 52Fair quality (C) · 52 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. | 82.7 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 59/100 (quality, fit, speed and memory use) sets the ranking. | 11.1 tok/s | Runs well |
| Phi-4 Multimodal Instruct | 44Fair quality (C) · 44 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. | 52.1 tok/s | Runs great | 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 |
| GLM-4 9B Chat (2024) | 48Fair quality (C) · 48 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. | 67.0 tok/s | Runs great | 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 |
| Qwen3 4B | 50Fair quality (C) · 50 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. | 72.2 tok/s | Runs great | 47Fair quality (C) · 47 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. | 16.3 tok/s | Runs well |
| Olmo 3 7B Instruct | 50Fair quality (C) · 50 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. | 86.3 tok/s | Runs great | 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 |
| DeepSeek V2 Lite Chat | 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. | 131 tok/s | Runs great | 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 |
| Granite 4.2 3B | 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 79.3 tok/s | Runs great | 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 17.9 tok/s | Runs well |
| Llama 3.2 11B Vision Instruct | 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 59.0 tok/s | Runs great | 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 10.1 tok/s | Runs well |
| GLM-Z1 9B (0414) | 58Good quality (B) · 58 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. | 67.0 tok/s | Runs great | 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 |
| GLiDE 9B | 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 79.3 tok/s | Runs great | 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 |
| Hermes 3 (Llama 3.1 8B) | 48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 78.4 tok/s | Runs great | 40Fair quality (C) · 40 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 |
| Llama 3.1 8B Instruct | 48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 78.4 tok/s | Runs great | 40Fair quality (C) · 40 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 |
| Apertus v1.5 8B | 46Fair quality (C) · 46 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. | 70.8 tok/s | Runs great | 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. | 12.1 tok/s | Runs well |
| Qwen2.5 7B Instruct 1M | 50Fair quality (C) · 50 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. | 82.7 tok/s | Runs great | 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. | 11.1 tok/s | Runs well |
| Qwen1.5 32B Chat | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 38.1 tok/s | Runs welltight fit | 30Basic quality (D) · 30 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. | 3.3 tok/s | Slow |
| Falcon-H1 7B Instruct | 50Fair quality (C) · 50 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. | 83.0 tok/s | Runs great | 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. | 11.1 tok/s | Runs well |
| Seed-Coder 8B Reasoning | 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 76.4 tok/s | Runs great | 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 |
| LFM2 8B-A1B | 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 105 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 38.0 tok/s | Runs great |
| Mistral 7B Instruct v0.3 | 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 40.0 tok/s | Runs great | 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 |
| Granite 3.2 8B Instruct | 46Fair quality (C) · 46 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. | 77.1 tok/s | Runs great | 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 |
| Granite 3.3 8B | 46Fair quality (C) · 46 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. | 77.1 tok/s | Runs great | 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 |
| MiniCPM-V 2.6 8B | 48Fair quality (C) · 48 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. | 77.8 tok/s | Runs great | 40Fair quality (C) · 40 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 |
| Nemotron 3 Nano 4B | 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 73.1 tok/s | Runs great | 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 |
| Ministral 8B (2410) | 46Fair quality (C) · 46 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. | 78.5 tok/s | Runs great | 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 |
| DeepHermes 3 Llama 3 8B Preview | 46Fair quality (C) · 46 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. | 78.4 tok/s | Runs great | 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 |
| Dolphin 3.0 Llama 3.1 8B | 46Fair quality (C) · 46 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. | 78.4 tok/s | Runs great | 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 |
| Tülu 3 8B | 46Fair quality (C) · 46 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. | 78.4 tok/s | Runs great | 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 |
| LLaVA 1.6 34B | 36Basic quality (D) · 36 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. | 46.0 tok/s | Runs great | 30Basic quality (D) · 30 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 |
| CogVLM2 Llama 3 Chat 19B | 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. | 52.4 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow |
| Nous Hermes 2 SOLAR 10.7B | 40Fair quality (C) · 40 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. | 58.7 tok/s | Runs great | 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 |
| SOLAR 10.7B Instruct | 40Fair quality (C) · 40 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. | 58.7 tok/s | Runs great | 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 |
| EXAONE 3.5 7.8B | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 80.6 tok/s | Runs great | 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 |
| Seed-Coder 8B Instruct | 56Good quality (B) · 56 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. | 76.4 tok/s | Runs great | 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 10.3 tok/s | Runs well |
| Llama 3.1 Nemotron Nano 4B v1.1 | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 64.4 tok/s | Runs great | 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. | 14.5 tok/s | Runs well |
| Hermes 2 Pro Mistral 7B | 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 30Basic quality (D) · 30 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 |
| Starling LM 7B Beta | 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 30Basic quality (D) · 30 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 |
| Granite 3.1 8B Instruct | 44Fair quality (C) · 44 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. | 77.1 tok/s | Runs great | 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 |
| Falcon 3 7B Instruct | 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. | 84.4 tok/s | Runs great | 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 |
| EXAONE Deep 7.8B | 56Good quality (B) · 56 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. | 80.6 tok/s | Runs great | 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 |
| Qwen3 4B Thinking 2507 | 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 72.2 tok/s | Runs great | 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 |
| InternVL2 8B | 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. | 78.0 tok/s | Runs great | 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 |
| OpenChat 3.5 (0106) | 35Basic quality (D) · 35 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| Dolphin 2.9.4 Llama 3.1 8B | 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. | 78.4 tok/s | Runs great | 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 |
| Hermes 2 Pro Llama 3 8B | 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. | 78.4 tok/s | Runs great | 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 |
| OpenChat 3.6 8B | 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. | 78.4 tok/s | Runs great | 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 |
| Aya Vision 8B | 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. | 73.0 tok/s | Runs great | 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 |
| Mistral-NeMo-Minitron 8B Instruct | 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. | 74.9 tok/s | Runs great | 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 |
| Gemma 3 4B IT | 45Fair quality (C) · 45 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 67.5 tok/s | Runs great | 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 |
| Qwen2-VL 7B Instruct | 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. | 76.0 tok/s | Runs great | 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 |
| Nous Hermes 2 Mixtral 8x7B DPO | 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 106 tok/s | Runs welltight fit | 51Fair quality (C) · 51 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. | 3.5 tok/s | Slow |
| LFM3 1.7B | 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 168 tok/s | Runs great | 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 |
| Yi 34B Chat | 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. | 36.0 tok/s | Runs welltight fit | 28Basic quality (D) · 28 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. | 3.1 tok/s | Slow |
| Mistral 7B Instruct v0.2 | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| Nous Hermes 2 Mistral 7B DPO | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| OpenChat 3.5 (1210) | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| Phi-3.5 Mini Instruct | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 76.0 tok/s | Runs great | 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 |
| Qwen1.5 14B Chat | 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. | 60.6 tok/s | Runs great | 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.6 tok/s | Slow |
| Phi-3 Small 8K Instruct | 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. | 85.2 tok/s | Runs great | 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. | 11.4 tok/s | Runs well |
| Command R7B | 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. | 78.4 tok/s | Runs great | 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 |
| MedGemma 4B IT | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 67.5 tok/s | Runs great | 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 |
| Falcon-H1R 7B | 56Good quality (B) · 56 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. | 83.0 tok/s | Runs great | 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 |
| Phi-4 Mini (3.8B) | 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. | 75.6 tok/s | Runs great | 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 |
| Phi-3.5 Vision Instruct | 38Basic quality (D) · 38 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. | 70.0 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 tok/s | Runs well |
| Hunyuan 4B Instruct | 42Fair quality (C) · 42 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. | 68.8 tok/s | Runs great | 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 |
| Olmo 3 7B Think | 54Fair quality (C) · 54 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. | 86.3 tok/s | Runs great | 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 |
| Llama 3 8B Instruct | 42Fair quality (C) · 42 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. | 78.4 tok/s | Runs great | 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 |
| Ministral 3 3B | 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. | 75.4 tok/s | Runs great | 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 |
| Jamba 1.5 Mini | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 111 tok/s | Runs welltight fit | 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slow |
| Mixtral 8x7B Instruct | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 106 tok/s | Runs welltight fit | 49Fair quality (C) · 49 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. | 3.5 tok/s | Slow |
| Qwen2 7B Instruct | 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. | 82.7 tok/s | Runs great | 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 |
| Qwen2.5 Coder 7B Instruct | 55Good quality (B) · 55 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. | 82.7 tok/s | Runs great | 46Fair quality (C) · 46 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 |
| Granite 4.1 3B | 46Fair quality (C) · 46 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. | 85.4 tok/s | Runs great | 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 |
| Qianfan-OCR 4B | 50Fair quality (C) · 50 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. | 61.2 tok/s | Runs great | 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 |
| OpenHermes 2.5 Mistral 7B | 32Basic quality (D) · 32 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. | 40.1 tok/s | Runs great | 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 |
| Starling LM 7B Alpha | 32Basic quality (D) · 32 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. | 40.1 tok/s | Runs great | 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 |
| Foundation-Sec 8B Reasoning | 52Fair quality (C) · 52 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. | 78.4 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 54/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well |
| OpenReasoning Nemotron 7B | 54Fair quality (C) · 54 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. | 82.7 tok/s | Runs great | 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 |
| AFM 4.5B | 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. | 62.8 tok/s | Runs great | 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 |
| Command R7B Arabic | 42Fair quality (C) · 42 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. | 78.4 tok/s | Runs great | 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 |
| 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 74/100 (quality, fit, speed and memory use) sets the ranking. | 41.9 tok/s | Runs welloffloads to RAM | 64Good quality (B) · 64 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. | 11.5 tok/s | Runs well |
| Apertus 8B Instruct | 40Fair quality (C) · 40 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. | 78.2 tok/s | Runs great | 33Basic quality (D) · 33 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 |
| Aya Expanse 8B | 40Fair quality (C) · 40 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. | 78.4 tok/s | Runs great | 33Basic quality (D) · 33 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 |
| Chandra OCR 2 | 48Fair quality (C) · 48 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. | 54.8 tok/s | Runs great | 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well |
| Granite 3.0 8B Instruct | 40Fair quality (C) · 40 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. | 77.1 tok/s | Runs great | 33Basic quality (D) · 33 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. | 10.4 tok/s | Runs well |
| Kolibri 1 (78B-A3.5B) | 63Good quality (B) · 63 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. | 83.9 tok/s | Runs welloffloads to RAM | 90Excellent quality (A+) · 90 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. | 12.5 tok/s | Runs well |
| InternLM2.5 7B Chat | 40Fair quality (C) · 40 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. | 81.4 tok/s | Runs great | 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 |
| Gemma 3n E2B | 36Basic quality (D) · 36 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. | 145 tok/s | Runs great | 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 |
| Mistral 7B Instruct v0.1 | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| DeepSeek R1 Distill Llama 8B | 50Fair quality (C) · 50 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. | 78.4 tok/s | Runs great | 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. | 10.5 tok/s | Runs well |
| Phi-3 Mini 128K Instruct | 36Basic quality (D) · 36 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. | 76.0 tok/s | Runs great | 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 |
| Fara 7B | 50Fair quality (C) · 50 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. | 76.0 tok/s | Runs great | 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 |
| Phi-3 Vision 128K Instruct | 34Basic quality (D) · 34 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. | 70.0 tok/s | Runs great | 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 |
| Dolphin 2.9 Llama 3 8B | 38Basic quality (D) · 38 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. | 78.4 tok/s | Runs great | 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 |
| LFM3-VL 2B | 50Fair quality (C) · 50 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. | 151 tok/s | Runs great | 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 |
| DeepSeek Prover V2 7B | 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. | 42.0 tok/s | Runs great | 33Basic quality (D) · 33 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. | 12.2 tok/s | Runs well |
| StarCoder2 15B Instruct | 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 39.5 tok/s | Runs great | 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 |
| Voxtral Mini 3B | 36Basic quality (D) · 36 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. | 62.0 tok/s | Runs great | 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 |
| InternLM2 Math Plus 20B | 39Basic quality (D) · 39 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. | 43.2 tok/s | Runs great | 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Jamba Reasoning 3B | 44Fair quality (C) · 44 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. | 90.7 tok/s | Runs great | 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 |
| LFM2.5-VL 3B | 44Fair quality (C) · 44 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. | 93.0 tok/s | Runs great | 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 |
| S5 nano | 37Basic quality (D) · 37 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. | 62.3 tok/s | Runs great | 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 |
| Neural Chat 7B v3.3 | 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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. | 11.7 tok/s | Runs well |
| Orca 2 13B | 28Basic quality (D) · 28 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 | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow |
| StableLM 2 12B Chat | 28Basic quality (D) · 28 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. | 51.9 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 tok/s | Slow |
| OLMo 2 7B Instruct | 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. | 86.3 tok/s | Runs great | 30Basic quality (D) · 30 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. | 11.6 tok/s | Runs well |
| WeVisOne-VL 4B | 45Fair quality (C) · 45 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. | 60.1 tok/s | Runs great | 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 |
| CodeGeeX4 All 9B | 46Fair quality (C) · 46 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. | 67.0 tok/s | Runs great | 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 |
| LightOnOCR-3 4B | 48Fair quality (C) · 48 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. | 63.9 tok/s | Runs great | 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 |
| Yi 1.5 9B Chat | 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. | 71.3 tok/s | Runs great | 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 |
| EXAONE 3.0 7.8B Instruct | 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. | 80.6 tok/s | Runs great | 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 |
| North Micro Vision | 44Fair quality (C) · 44 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. | 117 tok/s | Runs great | 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. | 26.4 tok/s | Runs well |
| SmolLM3 3B | 42Fair quality (C) · 42 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. | 94.3 tok/s | Runs great | 39Basic quality (D) · 39 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. | 21.2 tok/s | Runs well |
| Zamba2 7B Instruct | 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. | 85.6 tok/s | Runs great | 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 |
| RecurrentGemma 9B IT | 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. | 65.4 tok/s | Runs great | 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 |
| MiniCPM3 4B | 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 71.3 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 16.1 tok/s | Runs well |
| Granite 4.0 Micro (3B) | 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 85.4 tok/s | Runs great | 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 |
| LFM2.5 2.6B | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 108 tok/s | Runs great | 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 |
| Phi-3 Mini 4K Instruct | 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 76.0 tok/s | Runs great | 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 |
| Baichuan 2 13B Chat | 26Basic quality (D) · 26 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. | 45.3 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 4.7 tok/s | Slow |
| DeepSeek MoE 16B Chat | 26Basic quality (D) · 26 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. | 121 tok/s | Runs great | 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. | 27.5 tok/s | Runs well |
| Llama 2 13B Chat | 26Basic quality (D) · 26 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. | 48.4 tok/s | Runs great | 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow |
| OLMoE 1B-7B Instruct | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 113 tok/s | Runs great | 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 |
| Zephyr 7B Beta | 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 40.1 tok/s | Runs great | 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 |
| Gemma 1.1 7B IT | 28Basic quality (D) · 28 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. | 73.8 tok/s | Runs great | 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 |
| DeepSeek Coder 33B Instruct | 36Basic quality (D) · 36 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. | 48.0 tok/s | Runs great | 30Basic quality (D) · 30 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 |
| Qwen3-Next 80B-A3B Thinking | 72Great quality (A) · 72 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. | 58.9 tok/s | Slowheavy RAM offload | 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well |
| Jamba2 3B | 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 95.8 tok/s | Runs great | 39Basic quality (D) · 39 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. | 21.6 tok/s | Runs well |
| Falcon3 Mamba 7B Instruct | 38Basic quality (D) · 38 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. | 86.6 tok/s | Runs great | 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 |
| Aya 23 8B | 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. | 78.4 tok/s | Runs great | 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 |
| Yi 1.5 6B Chat | 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 47.9 tok/s | Runs great | 26Basic quality (D) · 26 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. | 10.8 tok/s | Runs well |
| Qwen2.5-Omni 3B | 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 52.4 tok/s | Runs great | 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 |
| Granite Code 20B Instruct | 35Basic quality (D) · 35 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. | 42.8 tok/s | Runs great | 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 |
| Phi-4 Mini Reasoning (3.8B) | 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 75.6 tok/s | Runs great | 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 |
| Qwen1.5 MoE A2.7B Chat | 24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 124 tok/s | Runs great | 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 |
| Qwen3 Next 80B-A3B Instruct | 70Great quality (A) · 70 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. | 58.9 tok/s | Slowheavy RAM offload | 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 tok/s | Runs well |
| Gemma 7B IT | 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 73.8 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | 12.6 tok/s | Runs well |
| DeepSeek R1 Distill Qwen 7B | 46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 82.7 tok/s | Runs great | 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 |
| Granite Code 34B Instruct | 38Basic quality (D) · 38 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. | 36.7 tok/s | Runs welltight fit | 28Basic quality (D) · 28 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 |
| Qwen1.5 7B Chat | 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 81.6 tok/s | Runs great | 21Basic quality (D) · 21 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. | 11.0 tok/s | Runs well |
| DeepSeek Coder 6.7B Instruct | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 43.1 tok/s | Runs great | 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 |
| Mathstral 7B | 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 40.0 tok/s | Runs great | 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 |
| Granite 4.0 H Micro | 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 91.0 tok/s | Runs great | 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 20.5 tok/s | Runs well |
| LLaVA 1.5 13B | 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 47.2 tok/s | Runs great | 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 |
| Orca 2 7B | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 43.1 tok/s | Runs great | 18Basic quality (D) · 18 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 |
| WizardLM 13B v1.2 | 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 48.4 tok/s | Runs great | 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 |
| Code Llama 34B Instruct | 36Basic quality (D) · 36 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. | 36.7 tok/s | Runs welltight fit | 26Basic quality (D) · 26 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. | 3.2 tok/s | Slow |
| Llama 3.2 3B Instruct | 35Basic quality (D) · 35 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. | 90.4 tok/s | Runs great | 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 |
| Qwen2.5-VL 3B Instruct | 34Basic quality (D) · 34 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 | 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 |
| Yi Coder 9B Chat | 40Fair quality (C) · 40 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. | 71.3 tok/s | Runs great | 28Basic quality (D) · 28 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 |
| LLM4Decompile 6.7B V2 | 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 43.1 tok/s | Runs great | 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. | 12.6 tok/s | Runs well |
| CodeGemma 7B | 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. | 73.8 tok/s | Runs great | 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 |
| StarCoder2 15B (base) | 32Basic quality (D) · 32 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. | 39.5 tok/s | Runs great | 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | Slow |
| Falcon-H1 3B Instruct | 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. | 92.2 tok/s | Runs great | 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 |
| Qwen3.5 2B | 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. | 128 tok/s | Runs great | 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 |
| Llama 2 7B Chat | 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. | 43.1 tok/s | Runs great | 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 |
| Vicuna 13B v1.5 | 20Basic quality (D) · 20 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. | 48.4 tok/s | Runs great | 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 |
| LLM4Decompile 9B V2 | 38Basic quality (D) · 38 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. | 71.3 tok/s | Runs great | 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 |
| SQLCoder 7B v2 | 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. | 43.1 tok/s | Runs great | 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 12.6 tok/s | Runs well |
| Llama 3.3 Nemotron Super 49B v1.5 | 56Good quality (B) · 56 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. | 31.2 tok/s | Runs welloffloads to RAM | 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. | 0.7 tok/s | Very slow |
| TMax 2B | 40Fair quality (C) · 40 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. | 154 tok/s | Runs great | 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 |
| Unlimited OCR 2 (3B-A0.6B) | 44Fair quality (C) · 44 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. | 155 tok/s | Runs great | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 45.8 tok/s | Runs great |
| Code Llama 13B Instruct | 29Basic quality (D) · 29 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. | 65.9 tok/s | Runs great | 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 tok/s | Slow |
| Qwen2.5 3B Instruct | 34Basic quality (D) · 34 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. | 93.9 tok/s | Runs great | 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 |
| Hermes 3 Llama 3.2 3B | 32Basic quality (D) · 32 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. | 90.4 tok/s | Runs great | 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 |
| DeepSeek LLM 7B Chat | 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. | 42.0 tok/s | Runs great | 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 |
| LLaVA 1.6 Mistral 7B | 28Basic quality (D) · 28 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. | 83.2 tok/s | Runs great | 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 |
| Qwen3-VL 2B Instruct | 36Basic quality (D) · 36 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. | 136 tok/s | Runs great | 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 |
| MiniCPM-V 4.7 1B | 40Fair quality (C) · 40 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. | 187 tok/s | Runs great | 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 |
| Falcon Mamba 7B Instruct | 30Basic quality (D) · 30 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. | 86.6 tok/s | Runs great | 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 |
| Yi 6B Chat | 20Basic quality (D) · 20 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. | 47.9 tok/s | Runs great | 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 |
| LLaVA 1.5 7B | 16Basic quality (D) · 16 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. | 41.1 tok/s | Runs great | 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 |
| Falcon 3 3B Instruct | 30Basic quality (D) · 30 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. | 89.9 tok/s | Runs great | 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 |
| LFM2 2.6B | 34Basic quality (D) · 34 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. | 113 tok/s | Runs great | 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 |
| WizardMath 7B v1.1 | 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. | 40.1 tok/s | Runs great | 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 |
| StarCoder 15B | 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. | 39.8 tok/s | Runs great | 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 |
| Unlimited OCR (3B-A0.6B) | 40Fair quality (C) · 40 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. | 155 tok/s | Runs great | 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 |
| Qwen3 Coder Next (80B-A3B) | 72Great quality (A) · 72 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. | 60.0 tok/s | Slowheavy RAM offload | 81Great quality (A) · 81 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. | 20.3 tok/s | Runs well |
| OLMo 7B Instruct | 14Basic quality (D) · 14 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. | 42.1 tok/s | Runs great | 9Basic quality (D) · 9 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. | 15.6 tok/s | Runs well |
| Vicuna 7B v1.5 | 14Basic quality (D) · 14 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. | 43.1 tok/s | Runs great | 9Basic quality (D) · 9 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. | 15.9 tok/s | Runs well |
| Qwen2.5-Math 7B Instruct | 36Basic quality (D) · 36 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. | 82.7 tok/s | Runs great | 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 |
| Code Llama 7B Instruct | 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. | 43.1 tok/s | Runs great | 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. | 12.6 tok/s | Runs well |
| StarCoder2 7B | 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. | 40.5 tok/s | Runs great | 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 |
| Granite 3.2 2B Instruct | 30Basic quality (D) · 30 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. | 115 tok/s | Runs great | 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 |
| Granite 3.3 2B | 30Basic quality (D) · 30 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. | 115 tok/s | Runs great | 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 |
| Granite Code 8B Instruct (128K) | 32Basic quality (D) · 32 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. | 78.2 tok/s | Runs great | 26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well |
| EXAONE 3.5 2.4B | 30Basic quality (D) · 30 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. | 120 tok/s | Runs great | 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 |
| Baichuan 2 7B Chat | 20Basic quality (D) · 20 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. | 83.9 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 tok/s | Runs well |
| Codestral Mamba 7B | 36Basic quality (D) · 36 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. | 86.4 tok/s | Runs great | 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 |
| Nemotron Mini 4B Instruct | 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 69.3 tok/s | Runs great | 18Basic quality (D) · 18 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. | 20.2 tok/s | Runs well |
| MiniCPM5 1B | 36Basic quality (D) · 36 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. | 269 tok/s | Runs great | 35Basic quality (D) · 35 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. | 42.0 tok/s | Runs great |
| InternLM2 Math Plus 7B | 32Basic quality (D) · 32 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. | 81.4 tok/s | Runs great | 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 |
| Falcon 40B Instruct | 11Basic quality (D) · 11 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. | 48.6 tok/s | Runs great | 15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slow |
| Qwen3 1.7B | 30Basic quality (D) · 30 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. | 143 tok/s | Runs great | 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 |
| Granite 3.1 2B Instruct | 28Basic quality (D) · 28 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. | 115 tok/s | Runs great | 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 |
| Gemma 2 2B | 28Basic quality (D) · 28 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. | 111 tok/s | Runs great | 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 |
| Granite Vision 3.2 2B | 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. | 97.4 tok/s | Runs great | 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 |
| WeVisOne VL 2B | 27Basic quality (D) · 27 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. | 119 tok/s | Runs great | 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 |
| Qwen2.5 Coder 3B Instruct | 36Basic quality (D) · 36 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. | 93.9 tok/s | Runs great | 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 |
| Granite 3.0 2B Instruct | 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. | 110 tok/s | Runs great | 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 |
| LFM2.5 1.2B Instruct | 32Basic quality (D) · 32 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. | 248 tok/s | Runs great | 31Basic quality (D) · 31 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. | 38.8 tok/s | Runs great |
| SmolVLM2 2.2B Instruct | 24Basic quality (D) · 24 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. | 129 tok/s | Runs great | 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 |
| TeleOCR | 40Fair quality (C) · 40 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. | 204 tok/s | Runs great | 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 |
| MiniCPM-OCR 1.0 1.3B | 42Fair quality (C) · 42 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. | 223 tok/s | Runs great | 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 |
| EXAONE 4.0 1.2B | 30Basic quality (D) · 30 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. | 227 tok/s | Runs great | 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 |
| Falcon 7B Instruct | 6Basic quality (D) · 6 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. | 40.2 tok/s | Runs great | 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 |
| PaddleOCR-VL 1.6 0.9B | 42Fair quality (C) · 42 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. | 302 tok/s | Runs great | 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 |
| Granite 3.1 3B-A800M Instruct | 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 140 tok/s | Runs great | 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. | 47.1 tok/s | Runs great |
| Ling Flash 2.0 (100B-A6B) | 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. | 38.2 tok/s | Slowheavy RAM offload | 72Great quality (A) · 72 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. | 10.4 tok/s | Runs well |
| SmolVLM 2.2B Instruct | 22Basic quality (D) · 22 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. | 129 tok/s | Runs great | 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 37.6 tok/s | Runs great |
| Granite 4.0 H 1B | 28Basic quality (D) · 28 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. | 199 tok/s | Runs great | 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 |
| Zamba2 2.7B Instruct | 22Basic quality (D) · 22 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. | 109 tok/s | Runs great | 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 |
| Qwen2-VL 2B Instruct | 24Basic quality (D) · 24 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. | 131 tok/s | Runs great | 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 |
| Falcon-H1 1.5B Instruct | 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. | 187 tok/s | Runs great | 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 |
| Granite 3.0 3B-A800M Instruct | 18Basic quality (D) · 18 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. | 140 tok/s | Runs great | 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 |
| Hunyuan A13B (80B-A13B) | 62Good quality (B) · 62 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. | 15.5 tok/s | Slowheavy RAM offload | 73Great quality (A) · 73 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. | 3.4 tok/s | Slow |
| LFM2 1.2B | 26Basic quality (D) · 26 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. | 248 tok/s | Runs great | 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 |
| Qwen2 57B-A14B Instruct | 35Basic quality (D) · 35 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. | 65.6 tok/s | Runs welloffloads to RAM | 49Fair quality (C) · 49 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. | 3.2 tok/s | Slow |
| Qwen2.5 1.5B Instruct | 24Basic quality (D) · 24 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. | 189 tok/s | Runs great | 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 |
| LFM2-VL 1.6B | 24Basic quality (D) · 24 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. | 184 tok/s | Runs great | 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 |
| InternLM 7B | 12Basic quality (D) · 12 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. | 86.1 tok/s | Runs great | 8Basic quality (D) · 8 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. | 14.7 tok/s | Runs well |
| StableLM Zephyr 3B | 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. | 104 tok/s | Runs great | 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 |
| Hunyuan 1.8B Instruct | 22Basic quality (D) · 22 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. | 162 tok/s | Runs great | 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 |
| SmolLM2 1.7B Instruct | 20Basic quality (D) · 20 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. | 170 tok/s | Runs great | 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 |
| Qwen3.5 0.8B | 26Basic quality (D) · 26 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. | 334 tok/s | Runs great | 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 |
| Granite Code 3B Instruct (128K) | 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | 83.4 tok/s | Runs great | 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 |
| Phi-2 2.7B | 16Basic quality (D) · 16 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. | 104 tok/s | Runs great | 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 |
| Solar Open 100B | 56Good quality (B) · 56 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. | 19.8 tok/s | Slowheavy RAM offload | 79Great quality (A) · 79 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. | 3.7 tok/s | Slow |
| Llama 3.2 1B Instruct | 22Basic quality (D) · 22 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. | 234 tok/s | Runs great | 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 |
| Sarvam 105B | 52Fair quality (C) · 52 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. | 24.0 tok/s | Slowheavy RAM offload | 52Fair quality (C) · 52 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. | 10.4 tok/s | Runs well |
| InternLM2.5 1.8B Chat | 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. | 154 tok/s | Runs great | 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 |
| Stable Code Instruct 3B | 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. | 104 tok/s | Runs great | 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 |
| Ring Flash 2.0 (100B-A6B) | 54Fair quality (C) · 54 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. | 38.2 tok/s | Slowheavy RAM offload | 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| GLiDE 2B | 17Basic quality (D) · 17 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. | 154 tok/s | Runs great | 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 |
| Falcon 3 1B Instruct | 16Basic quality (D) · 16 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. | 174 tok/s | Runs great | 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 |
| Gemma 3 1B | 20Basic quality (D) · 20 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. | 290 tok/s | Runs great | 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 |
| Spark X2.6 1.7B | 16Basic quality (D) · 16 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. | 170 tok/s | Runs great | 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 |
| Qwen2 1.5B Instruct | 16Basic quality (D) · 16 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. | 189 tok/s | Runs great | 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 |
| Gemma 2B IT | 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. | 116 tok/s | Runs great | 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 |
| DeepScaleR 1.5B Preview | 26Basic quality (D) · 26 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. | 163 tok/s | Runs great | 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 |
| SmolLM 1.7B Instruct | 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. | 170 tok/s | Runs great | 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 |
| Qwen2.5 Coder 1.5B Instruct | 26Basic quality (D) · 26 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. | 189 tok/s | Runs great | 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 |
| Command R 35B (v01) | 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. | 16.4 tok/s | Runs welloffloads to RAM | 37Basic quality (D) · 37 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 |
| OLMo 2 1B Instruct | 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. | 196 tok/s | Runs great | 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. | 44.2 tok/s | Runs great |
| LFM2 700M | 18Basic quality (D) · 18 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. | 392 tok/s | Runs great | 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 |
| Hermes 4 70B | 62Good quality (B) · 62 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. | 3.2 tok/s | Slowheavy RAM offload | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Llama 3.3 70B Instruct | 62Good quality (B) · 62 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. | 3.2 tok/s | Slowheavy RAM offload | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| StarCoder2 3B | 18Basic quality (D) · 18 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. | 95.8 tok/s | Runs great | 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 |
| DeepSeek R1 Distill Llama 70B | 60Good quality (B) · 60 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. | 3.2 tok/s | Slowheavy RAM offload | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Tülu 3 70B | 60Good quality (B) · 60 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. | 3.2 tok/s | Slowheavy RAM offload | 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Qwen3 0.6B | 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. | 387 tok/s | Runs great | 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 |
| Aya 23 35B | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 16.4 tok/s | Runs welloffloads to RAM | 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| DeepSeek R1 Distill Qwen 1.5B | 22Basic quality (D) · 22 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. | 163 tok/s | Runs great | 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 |
| StableLM 2 1.6B Chat | 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. | 177 tok/s | Runs great | 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 |
| StableLM 2 Zephyr 1.6B | 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. | 177 tok/s | Runs great | 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 |
| d1 2B | 21Basic quality (D) · 21 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. | 151 tok/s | Runs great | 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 |
| Llama 3.1 70B Instruct | 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 3.2 tok/s | Slowheavy RAM offload | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Falcon-H1 0.5B Instruct | 14Basic quality (D) · 14 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. | 558 tok/s | Runs great | 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 |
| Hermes 3 (Llama 3.1 70B) | 57Good quality (B) · 57 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. | 3.2 tok/s | Slowheavy RAM offload | 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Qwen2.5-Math 1.5B Instruct | 20Basic quality (D) · 20 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. | 189 tok/s | Runs great | 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 |
| 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. | 829 tok/s | Runs great | 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 |
| Yi Coder 1.5B Chat | 16Basic quality (D) · 16 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. | 196 tok/s | Runs great | 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 |
| GLiDE 0.8B | 11Basic quality (D) · 11 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. | 387 tok/s | Runs great | 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 |
| Llama 3.1 Nemotron 70B Instruct | 55Good quality (B) · 55 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. | 3.2 tok/s | Slowheavy RAM offload | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| LFM2-VL 450M | 12Basic quality (D) · 12 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. | 645 tok/s | Runs great | 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 |
| Apertus v1.5 70B | 55Good quality (B) · 55 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. | 3.0 tok/s | Slowheavy RAM offload | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| CodeGemma 2B | 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. | 116 tok/s | Runs great | 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 |
| 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. | 829 tok/s | Runs great | 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 |
| 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. | 854 tok/s | Runs great | 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 |
| SmolVLM 500M Instruct | 10Basic quality (D) · 10 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. | 569 tok/s | Runs great | 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 |
| Qwen2.5 72B Instruct | 51Fair quality (C) · 51 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. | 5.0 tok/s | Slowheavy RAM offload | 73Great quality (A) · 73 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Qwen2.5 0.5B Instruct | 10Basic quality (D) · 10 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. | 592 tok/s | Runs great | 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 |
| Qwen2.5-VL 72B Instruct | 51Fair quality (C) · 51 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. | 4.8 tok/s | Slowheavy RAM offload | 73Great quality (A) · 73 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Hunyuan 0.5B Instruct | 8Basic quality (D) · 8 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. | 538 tok/s | Runs great | 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 |
| InternVL3 78B | 51Fair quality (C) · 51 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. | 4.1 tok/s | Slowheavy RAM offload | 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow |
| 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. | 1,262 tok/s | Runs great | 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 |
| TinyLlama 1.1B Chat | 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. | 264 tok/s | Runs great | 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 |
| SmolLM2 360M Instruct | 8Basic quality (D) · 8 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. | 806 tok/s | Runs great | 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 |
| DeepSeek Coder 1.3B Instruct | 12Basic quality (D) · 12 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. | 215 tok/s | Runs great | 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 |
| LLM4Decompile 1.3B V2 | 12Basic quality (D) · 12 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. | 215 tok/s | Runs great | 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 |
| Apertus 70B Instruct | 50Fair quality (C) · 50 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. | 3.2 tok/s | Slowheavy RAM offload | 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 0.6 tok/s | Very slow |
| QVQ 72B Preview | 47Fair quality (C) · 47 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. | 4.8 tok/s | Slowheavy RAM offload | 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. | 0.5 tok/s | Very slow |
| Qwen2 0.5B Instruct | 6Basic quality (D) · 6 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. | 592 tok/s | Runs great | 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 |
| ERNIE 4.5 0.3B | 6Basic quality (D) · 6 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. | 806 tok/s | Runs great | 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 |
| Llama 3 70B Instruct | 48Fair quality (C) · 48 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. | 3.2 tok/s | Slowheavy RAM offload | 57Good quality (B) · 57 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. | 0.6 tok/s | Very slow |
| SmolVLM 256M Instruct | 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | 1,117 tok/s | Runs great | 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 |
| 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. | 1,075 tok/s | Runs great | 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 |
| surya ocr 2.5 | 15Basic quality (D) · 15 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. | 421 tok/s | Runs great | 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 |
| 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. | 806 tok/s | Runs great | 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 |
| Kimi Dev 72B | 56Good quality (B) · 56 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. | 5.0 tok/s | Slowheavy RAM offload | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Qwen2 72B Instruct | 44Fair quality (C) · 44 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. | 5.0 tok/s | Slowheavy RAM offload | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Qwen2-VL 72B Instruct | 44Fair quality (C) · 44 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. | 4.8 tok/s | Slowheavy RAM offload | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| 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. | 2,233 tok/s | Runs great | 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 |
| Llama 3.2 90B Vision Instruct | 46Fair quality (C) · 46 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. | 3.0 tok/s | Slowheavy RAM offload | 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.4 tok/s | Very slow |
| Qwen2.5-Math 72B Instruct | 40Fair quality (C) · 40 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. | 5.6 tok/s | Slowoffloads to RAM | 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 0.6 tok/s | Very slow |
| DeepSeek LLM 67B 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. | 7.0 tok/s | Slowoffloads to RAM | 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow |
| 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. | 3,226 tok/s | Runs great | 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 |
| 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. | 2,233 tok/s | Runs great | 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 |
| Llama 2 70B Chat | 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | 6.6 tok/s | Slowoffloads to RAM | 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow |
| Qwen2.5 Coder 0.5B Instruct | 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | 592 tok/s | Runs great | 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 |
| Code Llama 70B Instruct | 30Basic quality (D) · 30 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. | 6.6 tok/s | Slowoffloads to RAM | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | 0.7 tok/s | Very slow |
| gpt-oss 120B | 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 | 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 13.1 tok/s | Runs well |
| 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 | 82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 5.2 tok/s | Slowtight fit |
| 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 | 82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.5 tok/s | Very slowtight fit |
| 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 | 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| MiniMax M3.1 Flash (428B-A23B) | 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| 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 | 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. | 3.1 tok/s | Slow |
| GLM-5.3 Flash (320B-A18B) | 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 | 92Excellent quality (A+) · 92 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. | 3.6 tok/s | Slow |
| MiMo V2.6 Flash (310B-A15B) | 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 | 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| 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 | 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. | 5.2 tok/s | Slowtight fit |
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| Qwen3.8 Flash Next (125B-A6B) | 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 | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well |
| 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 | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| 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 | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.5 tok/s | Very slowtight fit |
| 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 | 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 2.0 tok/s | Very slowtight fit |
| 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| 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 | 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. | 3.3 tok/s | Slow |
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.5 tok/s | Very slowtight fit |
| Intern-S2 (397B-A17B) | 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 | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| 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 | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| Nex N2 Pro (397B-A17B) | 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 | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| 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 |
| Naive N0.5 Flash (309B-A15.5B) | 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 | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 3.4 tok/s | Slow |
| Qwen3.5 397B-A17B | 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 | 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| MiniMax M3 (427B) | 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 | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| 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 | 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| K2-Horizon (375B-A23B) | 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 | 79Great quality (A) · 79 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 |
| Hunyuan Hy3 (295B-A21B) | 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 | 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| 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 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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 | Slow |
| 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 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| Kimi K2.7 Code (1T) | 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| DeepSeek V4 Flash (284B-A13B) | 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 | 93Excellent quality (A+) · 93 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. | 3.4 tok/s | Slow |
| MiMo V2.5 (310B-A15B) | 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 | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| Ornith 1.5 397B-A17B | 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 | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Nemotron 3.5 Super VL 120B-A12B | 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 | 92Excellent quality (A+) · 92 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. | 3.7 tok/s | Slow |
| 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 | 89Excellent quality (A+) · 89 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. | 1.8 tok/s | Very slowtight fit |
| Inkling Small (276B-A12B) | 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 | 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 |
| 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 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | 2.6 tok/s | Very slowtight fit |
| 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 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| Step 3.7 Flash (198B-A11B) | 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 | 92Excellent quality (A+) · 92 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. | 4.1 tok/s | Slow |
| 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 | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| 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 | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| 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 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 71/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| 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 | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 tok/s | Very slowtight fit |
| 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 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 73/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| 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 | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| DeepSeek V4 Flash (April 2026) | 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 | 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. | 3.4 tok/s | Slow |
| Qwen3.5 122B-A10B | 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 70/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| Step 3.5 Flash (196B-A11B) | 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 | 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 tok/s | Slow |
| 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 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| 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 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| 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 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| Qwen3 235B-A22B Thinking 2507 | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 76Great quality (A) · 76 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. | 3.8 tok/s | Slow |
| Qwen3 Coder 480B-A35B | 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 tok/s | Slow |
| MiMo V2 Flash (309B-A15B) | 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 | 88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 2.1 tok/s | Very slowtight fit |
| 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 | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 tok/s | Very slowtight fit |
| Qwen3 235B-A22B Instruct 2507 | 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 75Great quality (A) · 75 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. | 3.8 tok/s | Slow |
| Solar Open 2 250B | 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 | 87Excellent quality (A+) · 87 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. | 3.6 tok/s | Slow |
| 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 76/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slowtight fit |
| MiniMax M2 (230B-A10B) | 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 10.4 tok/s | Runs well |
| Qwen3-VL 235B-A22B Instruct | 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 74Great quality (A) · 74 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow |
| Command A+ (218B-A25B) | 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 | 73Great quality (A) · 73 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. | 3.3 tok/s | Slow |
| K-EXAONE 236B-A23B | 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 | 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 tok/s | Slow |
| 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 | 73Great quality (A) · 73 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. | 3.1 tok/s | Slow |
| Nemotron 3 Super 120B-A12B | 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 | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow |
| Qwen3 235B-A22B | 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 | 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow |
| Devstral 2 (123B) | 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 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| InternVL3.5 241B-A28B | 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 | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow |
| Laguna S 2.1 (118B-A8B) | 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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. | 10.2 tok/s | Runs well |
| Llama 3.1 Nemotron Ultra 253B v1 | 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 | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow |
| Baichuan M3 235B-A22B | 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 | 70Great quality (A) · 70 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 tok/s | Slow |
| 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 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 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| 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 | 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 tok/s | Very slowtight fit |
| GLM-4.6V | 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 | 82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 tok/s | Slow |
| MiniMax-M1 80K | 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 | 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Command A Reasoning (111B) | 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 | 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| 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 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.3 tok/s | Slow |
| Ling 3.0 Flash (127B-A5B) | 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 | 79Great quality (A) · 79 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. | 10.2 tok/s | Runs well |
| MiniMax-M1 40K | 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 | 79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Mistral Small 4 (119B-A6B) | 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 | 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. | 10.5 tok/s | Runs well |
| Mistral Medium 3.5 (128B) | 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 | 80Great quality (A) · 80 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 |
| Trinity Large Thinking (400B-A13B) | 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 | 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. | 3.4 tok/s | Slow |
| Command A (111B) | 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 | 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| ERNIE 4.5 300B-A47B | 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 | 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. | 0.7 tok/s | Very slow |
| GLM-4.5V | 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 | 79Great quality (A) · 79 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. | 3.7 tok/s | Slow |
| Hermes 4 405B | 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 | 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow |
| Ling 2.6 Flash (104B-A7.4B) | 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | 11.0 tok/s | Runs well |
| Mistral Large 2.1 (2411) | 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 | 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. | 0.3 tok/s | Very slow |
| GLM-4.5 Air (106B-A12B) | 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 | 77Great quality (A) · 77 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. | 3.7 tok/s | Slow |
| Mistral Large 2 (123B) | 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 | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| NorthCUA Pro | 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 | 75Great quality (A) · 75 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. | 3.1 tok/s | Slow |
| Pixtral Large 124B (2411) | 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 | 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| dots.llm1 Instruct | 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 | 75Great quality (A) · 75 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. | 3.2 tok/s | Slow |
| MiniMax-Text-01 | 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 | 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Tülu 3 405B | 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 | 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow |
| 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 | 71Great quality (A) · 71 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. | 1.8 tok/s | Very slowtight fit |
| DeepSeek Coder V2 (236B) | 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 | 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. | 3.1 tok/s | Slow |
| Leanstral 119B-A6B | 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 | 62Good quality (B) · 62 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. | 12.5 tok/s | Runs well |
| DeepSeek Coder V2 Instruct (0614) | 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 | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| DeepSeek V2.5 1210 | 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 | 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Llama 3.1 405B Instruct | 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 | 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.1 tok/s | Very slow |
| Llama 4 Maverick (17B x 128E) | 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 | 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Llama 4 Scout 17B-16E | 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 | 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Command R+ (08-2024) 104B | 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 | 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| DeepSeek V2.5 | 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 | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Groot 65B A6B 261023 | 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 | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 10.5 tok/s | Runs well |
| Jamba 1.5 Large | 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 | 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 0.5 tok/s | Very slow |
| Ling 3.0 flash Sante | 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 | 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 12.3 tok/s | Runs well |
| Command R+ 104B (04-2024) | 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 | 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| DeepSeek V2 Chat | 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 | 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Mixtral 8x22B Instruct | 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 | 54Fair quality (C) · 54 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 tok/s | Very slow |
| Qwen1.5 110B Chat | 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 | 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 0.3 tok/s | Very slow |
| Grok-1 (314B) | 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 | 49Fair quality (C) · 49 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. | 0.5 tok/s | Very slow |
| Snowflake Arctic Instruct | 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 | 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 tok/s | Slow |
| Falcon 180B Chat | 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 | 33Basic quality (D) · 33 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. | 0.3 tok/s | Very slow |
Image models
57 of 60 image models run on the NVIDIA GeForce RTX 4090. 24.0 GB usable for models.
60 of 60 image models run on the Intel Xeon W-2100 series NAS (512 GB). 471 GB usable for models.
| Model | QualityRTX 4090 | SpeedRTX 4090 | RunsRTX 4090 | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS |
|---|---|---|---|---|---|---|
| Krea 2 Turbo | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 s | Runs great | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 min | Very slow |
| FLUX 3 Image Klein | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 6.6 s | Runs great | 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 5.5 min | Very slow |
| ERNIE-Image Turbo | 84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 3.7 s | Runs great | 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. | 3.1 min | Very slow |
| FLUX.2 [klein] 9B | 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | 1.6 s | Runs great | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 min | Slow |
| FLUX.1 Krea [dev] | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs great | 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. | 11.7 min | Very slow |
| FLUX.2 [klein] 4B | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 s | Runs great | 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. | 58 s | Slow |
| Z-Image Turbo | 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 2.9 s | Runs great | 82Great quality (A) · 82 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. | 2.2 min | Slow |
| FLUX.1 [dev] | 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs great | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 11.7 min | Very slow |
| MOSS-Image SFT | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 13 s | Runs great | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 13.6 min | Very slow |
| ERNIE-Image | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | 20 s | Runs well | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 21.4 min | Very slow |
| FLUX.1 Fill [dev] | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs great | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 12.1 min | Very slow |
| FLUX.1 Kontext [dev] | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 20 s | Runs well | 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. | 21.4 min | Very slow |
| Fibo 2.0 Dev | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 24 s | Runs wellencoder in RAM | 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 21.9 min | Very slow |
| Qwen-Image 2.1 Turbo | 87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | 11 s | Runs welltight fit · encoder in RAM | 89Excellent quality (A+) · 89 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. | 11.3 min | Very slow |
| FLUX.1 [schnell] | 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 s | Runs great | 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. | 1.9 min | Slow |
| Chroma1-HD | 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 18 s | Runs well | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 19.4 min | Very slow |
| Ideogram 4 | 85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 28 s | Runs welltight fit | 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 24.3 min | Very slow |
| Z-Image | 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 15 s | Runs well | 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 16.5 min | Very slow |
| Iris-3B | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | 16 s | Runs well | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 15.5 min | Very slow |
| Stable Diffusion 3.5 Large | 64Good quality (B) · 64 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. | 9.9 s | Runs great | 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. | 10.7 min | Very slow |
| HiDream-I1 Fast | 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 9.5 s | Runs greatencoder in RAM | 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. | 9.7 min | Very slow |
| Ming-Image 0.1 Design | 84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | 15 s | Runs welltight fit · encoder in RAM | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 15.8 min | Very slow |
| CogView4 6B | 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 16 s | Runs well | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 17.5 min | Very slow |
| Stable Diffusion 3.5 Large Turbo | 61Good quality (B) · 61 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 1.8 s | Runs great | 62Good quality (B) · 62 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. | 1.6 min | Slow |
| HiDream-I1 Dev | 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 16 s | Runs wellencoder in RAM | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | 16.5 min | Very slow |
| Kolors | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 s | Runs great | 60Good quality (B) · 60 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. | 3.9 min | Very slow |
| Stable Diffusion 3.5 Medium | 58Good quality (B) · 58 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. | 6.0 s | Runs great | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 5.8 min | Very slow |
| Lumina-Image 2.0 | 62Good quality (B) · 62 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. | 7.0 s | Runs great | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 6.8 min | Very slow |
| HiDream-I1 Full | 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | 43 s | Slowencoder in RAM | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 43.7 min | Very slow |
| FLUX.2 [dev] | 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 45 s | Slowtight fit · encoder in RAM | 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. | 35.0 min | Very slow |
| Stable Diffusion 3 Medium | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 3.1 s | Runs great | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.0 min | Very slow |
| Qwen-Image 2512 | 83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 1.9 min | Slowencoder in RAM | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | 87.5 min | Very slow |
| Stable Cascade | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 s | Runs great | 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. | 4.9 min | Very slow |
| OmniGen2 | 64Good quality (B) · 64 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. | 14 s | Runs well | 66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | 15.5 min | Very slow |
| Juggernaut XL v9 | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 4.5 s | Runs great | 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 |
| RealVisXL V5.0 | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 4.5 s | Runs great | 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 |
| FireRed-Image-Edit 1.1 | 80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | 1.7 min | Slowencoder in RAM | 87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 77.7 min | Very slow |
| Qwen-Image-Edit 2511 | 79Great quality (A) · 79 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. | 1.7 min | Slowencoder in RAM | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 77.7 min | Very slow |
| Animagine XL 4.0 | 60Good quality (B) · 60 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. | 4.2 s | Runs great | 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 |
| Illustrious XL v0.1 | 60Good quality (B) · 60 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. | 4.2 s | Runs great | 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 |
| Playground v2.5 | 60Good quality (B) · 60 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. | 7.5 s | Runs great | 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 7.3 min | Very slow |
| PixArt-Σ XL 1024 | 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 1.5 s | Runs great | 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 |
| DreamShaper XL v2 Turbo | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 1.3 s | Runs great | 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. | 76 s | Slow |
| Pony Diffusion V6 XL | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 3.8 s | Runs great | 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. | 3.7 min | Very slow |
| AuraFlow v0.3 | 56Good quality (B) · 56 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. | 13 s | Runs great | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 13.6 min | Very slow |
| Animagine XL 3.1 | 56Good quality (B) · 56 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 s | Runs great | 56Good quality (B) · 56 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | 4.1 min | Very slow |
| Stable Diffusion XL 1.0 | 55Good quality (B) · 55 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. | 4.5 s | Runs great | 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 |
| SDXL-Lightning (4-step) | 54Fair quality (C) · 54 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. | 0.7 s | Runs great | 52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | 37 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 72/100 (quality, fit, speed and memory use) sets the ranking. | 6.0 s | Runs great | 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 |
| Qwen-Image | 86Excellent quality (A+) · 86 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. | 1.8 min | SlowCPU offload | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 87.5 min | Very slow |
| SDXL Turbo | 40Fair quality (C) · 40 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. | 0.2 s | Runs great | 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 |
| Kandinsky 3 | 48Fair quality (C) · 48 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. | 9.5 s | Runs greatencoder in RAM | 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 8.7 min | Very slow |
| Realistic Vision V5.1 | 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 s | Runs great | 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 |
| DreamShaper 8 | 40Fair quality (C) · 40 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. | 1.2 s | Runs great | 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 |
| Stable Diffusion 1.5 | 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 1.2 s | Runs great | 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 |
| LCM DreamShaper v7 | 30Basic quality (D) · 30 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. | 0.3 s | Runs great | 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 |
| SD Turbo | 28Basic quality (D) · 28 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. | 0.1 s | Runs great | 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 |
| Cosmos3-Super Text2Image (64B) | 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 | 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. | 38.9 min | Very slow |
| HunyuanImage 3.0 (80B-A13B) | 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 | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 min | Very slow |
| Qwen-Image 2.1 | 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 | 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. | 58.3 min | Very slow |
Video models
31 of 43 video models run on the NVIDIA GeForce RTX 4090. 24.0 GB usable for models.
43 of 43 video models run on the Intel Xeon W-2100 series NAS (512 GB). 471 GB usable for models.
| Model | QualityRTX 4090 | SpeedRTX 4090 | RunsRTX 4090 | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS |
|---|---|---|---|---|---|---|
| LTX-2.5 (22B, video + audio) | 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 2.3 min | Runs greatCPU offload | 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. | 88.4 min | Very slow |
| Bernini-R A14B (video generation + editing) | 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | 11.3 min | Runs wellencoder in RAM | 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 11.7 h | Very slow |
| CogVideoX 5B I2V | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.7 min | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 2.9 h | Very slow |
| CogVideoX 5B | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | 2.7 min | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 2.9 h | Very slow |
| FramePack I2V (HunyuanVideo 13B) | 72Great quality (A) · 72 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. | 6.3 min | Runs wellencoder in RAM | 74Great quality (A) · 74 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. | 6.5 h | Very slow |
| HY-OmniWeaving (8.3B, unified video) | 74Great quality (A) · 74 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. | 8.3 min | Runs wellencoder in RAM | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 8.6 h | Very slow |
| LTX-Video 2B | 50Fair quality (C) · 50 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. | 25 s | Runs great | 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. | 24.3 min | Slow |
| 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 75/100 (quality, fit, speed and memory use) sets the ranking. | 5.4 min | Runs wellencoder in RAM | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | 5.0 h | Very slow |
| Wan 2.2 S2V 14B (speech to video) | 70Great quality (A) · 70 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. | 20.0 min | Slowtight fit | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | 16.2 h | Very slow |
| Wan 2.1 VACE 1.3B | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 min | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 4.2 h | Very slow |
| Wan 2.1 T2V 1.3B | 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | 3.6 min | Runs great | 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 h | Very slow |
| CogVideoX 2B | 45Fair quality (C) · 45 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. | 60 s | Runs great | 45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 min | Very slow |
| SkyReels V2 Diffusion Forcing 1.3B | 50Fair quality (C) · 50 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. | 4.5 min | Runs well | 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. | 4.9 h | Very slow |
| Wan 2.1 I2V 14B 480P | 68Good quality (B) · 68 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. | 18.0 min | Slowtight fit | 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 14.6 h | Very slow |
| LTX-2.3 | 84Great quality (A) · 84 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. | 7.8 min | Runs wellCPU offload | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | 6.5 h | Very slow |
| LTX-2 (19B, video + audio) | 80Great quality (A) · 80 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. | 7.8 min | Runs wellCPU offload | 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. | 6.5 h | Very slow |
| LTX-Video 13B 0.9.8 (distilled) | 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 70 s | Runs greatCPU offload | 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 58.3 min | Very slow |
| Cosmos-Predict2 2B Video2World | 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 3.9 min | Runs welltight fit · encoder in RAM | 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | 4.0 h | Very slow |
| MiniMax H3 (33B, video + audio) | 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | 20.3 min | Slowtight fit · CPU offload | 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | 16.8 h | Very slow |
| SCAIL-2 14B (character animation) | 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. | 26.0 min | SlowCPU offload | 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | 19.4 h | Very slow |
| Wan 2.2 I2V A14B | 84Great quality (A) · 84 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. | 31.2 min | Slowtight fit · CPU offload | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 h | Very slow |
| Wan 2.2 T2V A14B | 84Great quality (A) · 84 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. | 31.2 min | Slowtight fit · CPU offload | 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 h | Very slow |
| Mochi 1 Preview (10B) | 60Good quality (B) · 60 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. | 17.3 min | Slowtight fit · encoder in RAM | 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | 17.8 h | Very slow |
| SkyReels V2 T2V 14B 540P | 74Great quality (A) · 74 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. | 30.3 min | SlowCPU offload | 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 22.7 h | Very slow |
| Wan 2.2 TI2V 5B | 68Good quality (B) · 68 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. | 10.1 min | Runs welltight fit · CPU offload | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 8.4 h | Very slow |
| Wan 2.1 I2V 14B 720P | 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 39.0 min | Slowtight fit · CPU offload | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 32.4 h | Very slow |
| Wan 2.1 T2V 14B | 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 39.0 min | Slowtight fit · CPU offload | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 32.4 h | Very slow |
| 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. | 65.0 min | Very slowCPU offload | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 48.6 h | Very slow |
| Wan 2.2 Animate 14B | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 49.4 min | Very slowtight fit · CPU offload | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 30.8 h | Very slow |
| Wan 2.1 VACE 14B | 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 57.2 min | Very slowtight fit · CPU offload | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 35.6 h | Very slow |
| AnimateDiff v3 (SD 1.5) | 35Basic quality (D) · 35 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. | 20 s | Runs great | 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. | 19.4 min | Slow |
| Cosmos3-Super Image2Video (64B) | 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 | 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. | 36.4 h | Very slow |
| 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 11/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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. | 47.6 h | Very slow |
| HunyuanVideo 1.5 (8.3B) | 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 | 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | 29.2 h | Very slow |
| SkyReels V2 T2V 14B 720P | 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 | 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 h | Very slow |
| Step-Video T2V (30B) | 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 | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 50.2 h | Very slow |
| Wan-Dancer 14B (music to dance) | 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 | 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | 71.3 h | Very slow |
| Cosmos-Predict2 14B Video2World | 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 | 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | 25.9 h | Very slow |
| HunyuanVideo 13B | 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 | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 h | Very slow |
| HunyuanVideo I2V 13B | 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 | 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | 38.9 h | Very slow |
| 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 8/100 (quality, fit, speed and memory use) sets the ranking. | — | Won't run | 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. | 8.9 h | Very slow |
| CogVideoX 1.5 5B | 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 | 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. | 14.6 h | Very slow |
| Allegro (2.8B) | 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 | 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. | 19.4 h | Very slow |
Decision models
68 of 70 decision models run on the NVIDIA GeForce RTX 4090. 24.0 GB usable for models.
70 of 70 decision models run on the Intel Xeon W-2100 series NAS (512 GB). 471 GB usable for models.
| Model | QualityRTX 4090 | SpeedRTX 4090 | RunsRTX 4090 | QualityXeon W-2100 series NAS | SpeedXeon W-2100 series NAS | RunsXeon W-2100 series NAS |
|---|---|---|---|---|---|---|
| Qwen3 Reranker 4B | 90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | 52 ms | Runs great | 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 |
| Qwen3 Reranker 8B | 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | 88 ms | Runs great | 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 |
| zerank-2 | 88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | 52 ms | Runs great | 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 |
| Jina Reranker v3.5 | 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. | 11 ms | Runs great | 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 |
| Shieldstral 1.0 3B | 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. | 50 ms | Runs great | 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 |
| 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 92/100 (quality, fit, speed and memory use) sets the ranking. | 144 ms | Runs well | 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 |
| Intern-Decision 4B | 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. | 39 ms | Runs great | 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 |
| Jina Reranker v3 | 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. | 11 ms | Runs great | 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 |
| d1 3B | 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. | 28 ms | Runs great | 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 |
| mxbai-rerank-large v2 | 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. | 23 ms | Runs great | 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 |
| FRIDA-Decisions | 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. | 8.4 ms | Runs great | 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 |
| GLiNER2.5 Decide | 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. | 6.6 ms | Runs great | 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 |
| LemonDecider 4B | 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. | 28 ms | Runs great | 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 |
| Qwen3 Reranker 0.6B | 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. | 11 ms | Runs great | 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 |
| zerank-1 small | 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 | 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 |
| 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 90/100 (quality, fit, speed and memory use) sets the ranking. | 146 ms | Runs well | 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 |
| BGE Reranker v2 Gemma | 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | 34 ms | Runs great | 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 |
| Qwen3Guard Gen 4B | 84Great quality (A) · 84 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. | 84 ms | Runs great | 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 |
| Llama Prompt Guard 2 86M | 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. | 7.0 ms | Runs great | 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 |
| mxbai-rerank-base v2 | 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. | 9.9 ms | Runs great | 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 |
| Qwen3Guard Gen 8B | 85Excellent quality (A+) · 85 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. | 132 ms | Runs great | 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 |
| GLiClass ModernBERT Large v3 | 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. | 6.2 ms | Runs great | 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 |
| 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. | 4.3 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. | 48 ms | Runs great |
| Llama 3.1 Nemotron Safety Guard 8B v3 | 83Great quality (A) · 83 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. | 129 ms | Runs great | 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 |
| BGE Reranker v2 M3 | 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. | 10 ms | Runs great | 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 |
| DeBERTa v3 Large Zero-shot v2.0 | 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. | 6.4 ms | Runs great | 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 |
| DuoGuard 0.5B | 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. | 9.3 ms | Runs great | 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 |
| Skywork Reward V2 Qwen3 0.6B | 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. | 17 ms | Runs great | 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 |
| Granite Guardian 4.1 8B | 83Great quality (A) · 83 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. | 135 ms | Runs well | 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 |
| WildGuard 7B | 79Great quality (A) · 79 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. | 117 ms | Runs great | 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 |
| GTE Reranker ModernBERT Base | 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. | 5.6 ms | Runs great | 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 |
| Jina Reranker v2 Base Multilingual | 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. | 7.0 ms | Runs great | 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 |
| ModernBERT Large Zero-shot v2.0 | 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. | 6.2 ms | Runs great | 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 |
| Granite Guardian 3.3 8B | 79Great quality (A) · 79 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. | 131 ms | Runs great | 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 |
| GLiGuard 300M | 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. | 6.3 ms | Runs great | 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 |
| Granite Embedding Reranker English R2 | 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. | 5.6 ms | Runs great | 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 |
| Laya | 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. | 6.3 ms | Runs great | 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 |
| Llama Prompt Guard 2 22M | 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. | 4.8 ms | Runs great | 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 |
| NuExtract 2.0 4B | 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | 108 ms | Runs great | 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 |
| Qwen3Guard Gen 0.6B | 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. | 26 ms | Runs great | 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 |
| GLiClass Base v3 | 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. | 5.0 ms | Runs great | 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 |
| ProtectAI DeBERTa v3 Prompt Injection v2 | 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. | 5.9 ms | Runs great | 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 |
| NuExtract 2.0 2B | 70Great quality (A) · 70 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. | 98 ms | Runs great | 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 |
| DeBERTa v3 Base Zero-shot v2.0 | 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. | 5.0 ms | Runs great | 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 |
| ShieldGemma 9B | 64Good quality (B) · 64 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. | 98 ms | Runs great | 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 |
| GLiNER2 Base v1 | 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. | 5.1 ms | Runs great | 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 |
| HHEM 2.1 Open | 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. | 6.4 ms | Runs great | 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 |
| LettuceDetect Large | 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. | 13 ms | Runs great | 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 |
| Laya Multilingual | 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. | 5.7 ms | Runs great | 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 |
| ShieldGemma 2B | 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | 35 ms | Runs great | 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 |
| GLiNER Multi v2.1 | 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. | 5.6 ms | Runs great | 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 |
| Llama Guard 3 8B | 67Good quality (B) · 67 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. | 129 ms | Runs great | 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 |
| BART Large MNLI | 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. | 6.2 ms | Runs great | 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 |
| 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. | 4.2 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. | 45 ms | Runs great |
| ShieldGemma 27B | 62Good quality (B) · 62 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. | 260 ms | Runs well | 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 |
| Llama Guard 4 12B | 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 191 ms | Runs well | 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 |
| Llama Guard 3 1B | 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | 48 ms | Runs great | 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 |
| Nemotron Content Safety Reasoning 4B | 77Great quality (A) · 77 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. | 842 ms | Slow | 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 |
| gpt-oss-safeguard 20B | 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 1.0 s | Slow | 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 |
| DynaGuard 1.7B | 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | 284 ms | Runs well | 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 |
| DynaGuard 8B | 75Great quality (A) · 75 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. | 1.1 s | Slow | 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 |
| Selene 1 Mini 8B | 77Great quality (A) · 77 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. | 1.3 s | Slow | 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 |
| CompassJudger-2 7B | 75Great quality (A) · 75 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. | 1.3 s | Slow | 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 |
| CompassJudger-2 32B | 81Great quality (A) · 81 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. | 4.5 s | Very slowtight fit | 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 |
| GLIDER | 65Good quality (B) · 65 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. | 737 ms | Slow | 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 |
| Flow Judge v0.1 | 63Good quality (B) · 63 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. | 737 ms | Slow | 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 |
| Prometheus 2 7B | 65Good quality (B) · 65 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. | 1.2 s | Slow | 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 |
| Prometheus 2 8x7B | 70Great quality (A) · 70 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. | 7.4 s | Very slowoffloads to RAM | 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 |
| GLiDE 27B | 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 | 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 |
| gpt-oss-safeguard 120B | 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 | 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 |
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.