Intel Xeon Silver (4100 to 4300 series) NAS (256 GB) spec sheet
What the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB) can run
We check your GPU or device against every model. Browsers can’t see how much memory you have, so confirm your exact model below.
- Unified memory
- 256 GB
- Usable for models
- 230 GB
- Memory bandwidth
- 115 GB/s
- FP16 compute
- 1.0 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 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. | Qwen3.8 Flash Next (125B-A6B) | Q4_K_M | 129 GB | 11.0 tok/s | Runs well |
| 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. | Step 3.7 Flash (198B-A11B) | Q6_K | 185 GB | 4.3 tok/s | Slow |
| 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. | Step 3.5 Flash (196B-A11B) | Q6_K | 183 GB | 4.3 tok/s | Slow |
| 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. | Inkling Small (276B-A12B) | Q4_K_M | 182 GB | 5.6 tok/s | Slow |
| 91Excellent quality (A+) · 91 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. | MiMo V2.6 Flash (310B-A15B) | Q4_K_M | 209 GB | 4.5 tok/s | Slowtight fit |
| 92Excellent quality (A+) · 92 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. | GLM-5.3 Flash (320B-A18B) | Q4_K_M | 215 GB | 3.8 tok/s | Slowtight fit |
| 89Excellent quality (A+) · 89 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. | DeepSeek V4 Flash (284B-A13B) | Q4_K_M | 205 GB | 5.2 tok/s | Slowtight fit |
| 90Excellent quality (A+) · 90 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. | Naive N0.5 Flash (309B-A15.5B) | Q4_K_M | 208 GB | 4.4 tok/s | Slowtight fit |
| 89Excellent quality (A+) · 89 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. | MiMo V2.5 (310B-A15B) | Q4_K_M | 209 GB | 4.5 tok/s | Slowtight fit |
| 89Excellent quality (A+) · 89 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. | DeepSeek V4 Flash (April 2026) | Q5_K_M | 226 GB | 4.3 tok/s | Slowtight fit |
| 89Excellent quality (A+) · 89 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. | Hunyuan Hy3 (295B-A21B) | Q4_K_M | 204 GB | 3.2 tok/s | Slowtight fit |
| 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. | Nemotron 3.5 Super VL 120B-A12B | Q6_K | 121 GB | 3.9 tok/s | Slow |
| 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. | Solar Open 2 250B | Q4_K_M | 173 GB | 4.5 tok/s | Slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Thinking 2507 | Q4_K_M | 164 GB | 3.1 tok/s | Slow |
| 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. | MiMo V2 Flash (309B-A15B) | Q4_K_M | 208 GB | 4.5 tok/s | Slowtight 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. | Qwen3 235B-A22B Instruct 2507 | Q4_K_M | 164 GB | 3.1 tok/s | Slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 235B-A22B Instruct | Q4_K_M | 164 GB | 3.1 tok/s | Slow |
| 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. | Qwen3 235B-A22B | Q4_K_M | 164 GB | 3.1 tok/s | Slow |
| 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. | Nemotron 3 Super 120B-A12B | Q6_K | 120 GB | 3.9 tok/s | Slow |
| 86Excellent quality (A+) · 86 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. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 66.8 GB | 18.6 tok/s | Runs well |
| 80Great quality (A) · 80 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. | Intern-S2 (397B-A17B) | Q3_K_M | 217 GB | 5.1 tok/s | Slowtight fit |
| 79Great quality (A) · 79 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. | Nex N2 Pro (397B-A17B) | Q3_K_M | 214 GB | 5.1 tok/s | Slowtight fit |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3.1 Flash (428B-A23B) | Q3_K_M | 230 GB | 3.8 tok/s | Slowtight fit |
| 79Great quality (A) · 79 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. | Qwen3.5 397B-A17B | Q3_K_M | 217 GB | 5.1 tok/s | Slowtight fit |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 85.9 GB | 13.7 tok/s | Runs well |
| 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. | Baichuan M3 235B-A22B | Q4_K_M | 164 GB | 3.1 tok/s | Slow |
| 88Excellent quality (A+) · 88 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. | Qwen3.6 35B-A3B | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 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. | Devstral 2 (123B) | Q8_0 | 155 GB | 0.3 tok/s | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 397B-A17B | Q3_K_M | 217 GB | 5.1 tok/s | Slowtight fit |
| 88Excellent quality (A+) · 88 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. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 40.7 GB | 21.2 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q4_K_M | 43.5 GB | 25.1 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 68.8 GB | 21.2 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 67.8 GB | 21.2 tok/s | Runs well |
| 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | K2-Horizon (375B-A23B) | Q3_K_M | 207 GB | 3.8 tok/s | Slowtight fit |
| 87Excellent quality (A+) · 87 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. | Nex N2 Mini (35B-A3B) | Q4_K_M | 40.6 GB | 21.2 tok/s | Runs well |
| 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3 (427B) | Q3_K_M | 229 GB | 3.5 tok/s | Slowtight fit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 40.3 GB | 21.2 tok/s | Runs well |
| 79Great quality (A) · 79 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. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 68.8 GB | 21.2 tok/s | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 91Excellent quality (A+) · 91 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. | Gemma 4 26B-A4B | Q6_K | 40.6 GB | 12.0 tok/s | Runs well |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q4_K_M | 97.2 GB | 12.9 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q4_K_M | 41.1 GB | 21.2 tok/s | Runs well |
| 81Great quality (A) · 81 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. | Llama 3.1 Nemotron Ultra 253B v1 | Q4_K_M | 178 GB | 0.3 tok/s | Very slow |
| 75Great quality (A) · 75 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. | dots.llm1 Instruct | Q6_K | 144 GB | 3.4 tok/s | Slow |
| 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. | GLM-4.6V | Q6_K | 109 GB | 3.9 tok/s | Slow |
| 80Great quality (A) · 80 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. | Mistral Medium 3.5 (128B) | Q8_0 | 157 GB | 0.3 tok/s | Very slow |
| 83Great quality (A) · 83 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. | GLM-4.7 Flash (30B-A3B) | Q4_K_M | 38.5 GB | 21.2 tok/s | Runs well |
| 80Great quality (A) · 80 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. | Mistral Large 2.1 (2411) | Q8_0 | 152 GB | 0.3 tok/s | Very slow |
| 82Great quality (A) · 82 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. | Agents-A1 35B-A3B | Q4_K_M | 40.6 GB | 21.2 tok/s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen AgentWorld 35B-A3B | Q4_K_M | 40.3 GB | 21.2 tok/s | Runs well |
| 82Great quality (A) · 82 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. | Command A Reasoning (111B) | Q8_0 | 137 GB | 0.3 tok/s | Very slow |
| 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. | Mistral Small 4 (119B-A6B) | Q4_K_M | 92.1 GB | 11.0 tok/s | Runs well |
| 73Great quality (A) · 73 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. | K-EXAONE 236B-A23B | Q3_K_M | 136 GB | 3.8 tok/s | Slow |
| 78Great quality (A) · 78 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. | Mistral Large 2 (123B) | Q8_0 | 152 GB | 0.3 tok/s | Very slow |
| 78Great quality (A) · 78 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. | Pixtral Large 124B (2411) | Q8_0 | 153 GB | 0.3 tok/s | Very slow |
| 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. | GLM-4.5V | Q6_K | 109 GB | 3.9 tok/s | Slow |
| 87Excellent quality (A+) · 87 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. | Raon-1 mini Preview (30B-A4B) | Q6_K | 42.7 GB | 10.6 tok/s | Runs well |
| 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. | Command A (111B) | Q8_0 | 137 GB | 0.3 tok/s | Very slow |
| 80Great quality (A) · 80 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. | Hunyuan Hy-Memory 30B-A3B | Q4_K_M | 38.2 GB | 21.2 tok/s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 300B-A47B | Q4_K_M | 204 GB | 1.5 tok/s | Very slowtight 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. | DeepSeek Coder V2 (236B) | Q4_K_M | 163 GB | 3.2 tok/s | Slow |
| 79Great quality (A) · 79 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. | Solar Open 100B | Q6_K | 105 GB | 3.9 tok/s | Slow |
| 72Great quality (A) · 72 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. | InternVL3.5 241B-A28B | Q3_K_M | 139 GB | 3.1 tok/s | Slow |
| 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. | GLM-4.5 Air (106B-A12B) | Q6_K | 111 GB | 3.9 tok/s | Slow |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Large Thinking (400B-A13B) | Q3_K_M | 215 GB | 6.7 tok/s | Slowtight fit |
| 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. | Command A+ (218B-A25B) | Q3_K_M | 126 GB | 3.5 tok/s | Slow |
| 77Great quality (A) · 77 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. | Laguna XS 2.1 (33B-A3B) | Q4_K_M | 40.8 GB | 21.2 tok/s | Runs well |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Instruct (0614) | Q4_K_M | 163 GB | 3.2 tok/s | Slow |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 1210 | Q4_K_M | 163 GB | 3.2 tok/s | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Ring Flash 2.0 (100B-A6B) | Q4_K_M | 82.3 GB | 10.8 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 | Q4_K_M | 163 GB | 3.2 tok/s | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | North Mini Code 1.0 (30B-A3B) | Q4_K_M | 37.9 GB | 21.2 tok/s | Runs well |
| 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. | GLM-4.7 (355B-A32B) | Q2_K | 165 GB | 3.5 tok/s | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Beam 1.0 (501B-A23B) | Q2_K | 220 GB | 4.7 tok/s | Slowtight fit |
| 65Good quality (B) · 65 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. | NorthCUA Pro | Q3_K_M | 214 GB | 5.1 tok/s | Slowtight fit |
| 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. | MiniMax M2.7 (230B-A10B) | Q2_K | 113 GB | 10.9 tok/s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Ling Flash 2.0 (100B-A6B) | Q4_K_M | 82.3 GB | 10.8 tok/s | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Leanstral 119B-A6B | Q4_K_M | 92.1 GB | 10.2 tok/s | Runs well |
| 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. | MiniMax M2.5 (230B-A10B) | Q2_K | 113 GB | 10.9 tok/s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Cascade 2 30B-A3B | Q4_K_M | 38.3 GB | 18.4 tok/s | Runs well |
| 72Great quality (A) · 72 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. | Laguna S 2.1 (118B-A8B) | Q3_K_M | 78.2 GB | 10.7 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q4_K_M | 31.5 GB | 39.9 tok/s | Runs great |
| 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. | MiniMax M2.1 (230B-A10B) | Q2_K | 113 GB | 10.9 tok/s | Runs well |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Thinking 2507 | Q4_K_M | 38.5 GB | 19.4 tok/s | Runs well |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 30B-A3B | Q4_K_M | 38.5 GB | 19.4 tok/s | Runs well |
| 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. | Kimi Dev 72B | Q8_0 | 98.8 GB | 0.5 tok/s | Very slow |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Linear 48B-A3B | Q4_K_M | 49.1 GB | 21.2 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 flash Sante | Q4_K_M | 96.9 GB | 12.9 tok/s | Runs well |
| 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Instruct 2507 | Q4_K_M | 38.5 GB | 19.4 tok/s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2 (230B-A10B) | Q2_K | 113 GB | 10.9 tok/s | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 24B-A2B | Q4_K_M | 33.8 GB | 25.6 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Groot 65B A6B 261023 | Q4_K_M | 91.4 GB | 11.0 tok/s | Runs well |
| 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 30B-A3B | Q4_K_M | 38.3 GB | 18.4 tok/s | Runs well |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 480B-A35B | Q2_K | 213 GB | 3.2 tok/s | Slowtight fit |
| 72Great quality (A) · 72 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. | Qwen3-VL 30B-A3B Thinking | Q4_K_M | 38.8 GB | 19.4 tok/s | Runs well |
| 60Good quality (B) · 60 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. | Llama 4 Maverick (17B x 128E) | Q3_K_M | 217 GB | 5.1 tok/s | Slowtight 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. | DiffusionGemma 26B-A4B IT | Q4_K_M | 35.2 GB | 16.2 tok/s | Runs well |
| 73Great quality (A) · 73 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. | Hunyuan A13B (80B-A13B) | Q6_K | 86.0 GB | 3.6 tok/s | Slow |
| 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ (08-2024) 104B | Q8_0 | 131 GB | 0.3 tok/s | Very slow |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 30B-A3B Instruct | Q4_K_M | 38.8 GB | 19.4 tok/s | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B | Q4_K_M | 38.4 GB | 19.4 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Sarvam 30B | Q4_K_M | 38.8 GB | 26.1 tok/s | Runs well |
| 58Good quality (B) · 58 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. | GLM-4.6 (355B-A32B) | Q2_K | 165 GB | 3.5 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Chat | Q4_K_M | 163 GB | 3.2 tok/s | Slow |
| 68Good quality (B) · 68 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. | Nemotron 3.5 Lightning 30B-A3B | Q4_K_M | 38.3 GB | 21.2 tok/s | Runs well |
| 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Llama 4 Scout 17B-16E | Q5_K_M | 97.7 GB | 3.3 tok/s | Slow |
| 67Good quality (B) · 67 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. | Ling 2.6 Flash (104B-A7.4B) | Q3_K_M | 71.7 GB | 11.5 tok/s | Runs well |
| 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. | Llama 3.3 Nemotron Super 49B v1.5 | Q8_0 | 74.6 GB | 0.7 tok/s | Very slow |
| 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. | InternVL3 78B | Q8_0 | 105 GB | 0.4 tok/s | Very slow |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 405B | Q3_K_M | 222 GB | 0.2 tok/s | Very slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5 (355B-A32B) | Q2_K | 165 GB | 3.5 tok/s | Slow |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 31.2 GB | 19.1 tok/s | Runs well |
| 82Great quality (A) · 82 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. | Gemma 4 12B | Q6_K | 29.5 GB | 4.0 tok/s | Slow |
| 74Great quality (A) · 74 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. | Llama 3.3 70B Instruct | Q8_0 | 96.6 GB | 0.5 tok/s | Very slow |
| 74Great quality (A) · 74 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. | Hermes 4 70B | Q8_0 | 96.5 GB | 0.5 tok/s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Omni 30B-A3B Instruct | Q4_K_M | 41.3 GB | 19.4 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 26.6 GB | 25.1 tok/s | Runs well |
| 73Great quality (A) · 73 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. | Qwen2.5-VL 72B Instruct | Q8_0 | 99.5 GB | 0.5 tok/s | Very slow |
| 73Great quality (A) · 73 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. | Qwen2.5 72B Instruct | Q8_0 | 98.8 GB | 0.5 tok/s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B Thinking | Q4_K_M | 32.8 GB | 21.2 tok/s | Runs well |
| 64Good quality (B) · 64 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. | Ornith 1.5 122B-A10B | Q2_K | 69.3 GB | 10.9 tok/s | Runs well |
| 58Good quality (B) · 58 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. | MiniMax-M1 80K | Q2_K | 202 GB | 2.4 tok/s | Very slowtight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 405B | Q3_K_M | 222 GB | 0.2 tok/s | Very slowtight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 122B-A10B | Q2_K | 69.3 GB | 10.9 tok/s | Runs well |
| 72Great quality (A) · 72 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. | DeepSeek R1 Distill Llama 70B | Q8_0 | 96.5 GB | 0.5 tok/s | Very slow |
| 72Great quality (A) · 72 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. | Tülu 3 70B | Q8_0 | 96.5 GB | 0.5 tok/s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 27B | Q3_K_M | 33.2 GB | 3.2 tok/s | Slow |
| 57Good quality (B) · 57 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. | MiniMax-M1 40K | Q2_K | 202 GB | 2.4 tok/s | Very slowtight fit |
| 64Good quality (B) · 64 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. | Command R+ 104B (04-2024) | Q8_0 | 131 GB | 0.3 tok/s | Very slow |
| 58Good quality (B) · 58 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. | Ling 3.0 Tiny (8B-A1.3B) | Q5_K_M | 24.9 GB | 37.8 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 27B | Q3_K_M | 33.2 GB | 3.2 tok/s | Slow |
| 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. | Llama 3.1 70B Instruct | Q8_0 | 96.6 GB | 0.5 tok/s | Very slow |
| 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. | Llama 3.2 90B Vision Instruct | Q8_0 | 116 GB | 0.4 tok/s | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Large | Q3_K_M | 215 GB | 0.9 tok/s | Very slowtight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 27B | Q3_K_M | 33.2 GB | 3.2 tok/s | Slow |
| 62Good quality (B) · 62 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. | Trinity Mini (26B-A3B) | Q4_K_M | 35.1 GB | 21.2 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 405B Instruct | Q3_K_M | 222 GB | 0.2 tok/s | Very slowtight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q2_K | 49.1 GB | 12.1 tok/s | Runs well |
| 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. | QVQ 72B Preview | Q8_0 | 99.5 GB | 0.5 tok/s | Very slow |
| 68Good quality (B) · 68 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. | Hermes 3 (Llama 3.1 70B) | Q8_0 | 96.5 GB | 0.5 tok/s | Very slow |
| 75Great quality (A) · 75 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. | InternVL3.5 38B | Q6_K | 52.7 GB | 1.2 tok/s | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q4_K_M | 22.2 GB | 29.8 tok/s | Runs well |
| 53Fair quality (C) · 53 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. | MiniMax-Text-01 | Q2_K | 202 GB | 2.4 tok/s | Very slowtight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q4_K_M | 24.0 GB | 15.2 tok/s | Runs well |
| 75Great quality (A) · 75 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. | TMax 27B | Q3_K_M | 33.0 GB | 3.2 tok/s | Slow |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B | Q4_K_M | 32.9 GB | 21.2 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Axion 1.0 35B | Q4_K_M | 40.6 GB | 21.2 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 70B | Q8_0 | 98.0 GB | 0.5 tok/s | Very slow |
| 64Good quality (B) · 64 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. | Nemotron Labs Dory 1.0 4B | Q4_K_M | 21.9 GB | 17.2 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron 70B Instruct | Q8_0 | 96.5 GB | 0.5 tok/s | Very slow |
| 64Good quality (B) · 64 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. | Nanbeige4.2 3B | Q4_K_M | 23.1 GB | 16.5 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q4_K_M | 20.2 GB | 39.7 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 65/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 27B | Q3_K_M | 33.0 GB | 3.2 tok/s | Slow |
| 54Fair quality (C) · 54 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. | Mixtral 8x22B Instruct | Q6_K | 136 GB | 1.2 tok/s | Very slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q4_K_M | 24.0 GB | 15.2 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 72B Instruct | Q8_0 | 99.5 GB | 0.5 tok/s | Very slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 72B Instruct | Q8_0 | 98.8 GB | 0.5 tok/s | Very slow |
| 56Good quality (B) · 56 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. | NorthCUA Mini | Q4_K_M | 40.6 GB | 21.2 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Ling Mini 2.0 (16B-A1.4B) | Q4_K_M | 29.3 GB | 42.1 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 65/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q4_K_M | 20.9 GB | 27.2 tok/s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q4_K_M | 21.8 GB | 16.7 tok/s | Runs well |
| 72Great quality (A) · 72 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. | UI-Mate 27B | Q3_K_M | 33.0 GB | 3.2 tok/s | Slow |
| 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. | LFM2 24B-A2B | Q4_K_M | 33.7 GB | 27.1 tok/s | Runs well |
| 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Plus (14B) | Q6_K | 32.7 GB | 3.2 tok/s | Slow |
| 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Apriel 1.5 15B Thinker | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 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. | LFM2.5 8B-A1B | Q4_K_M | 24.3 GB | 39.6 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 64/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Thinking 2506 | Q4_K_M | 29.3 GB | 21.2 tok/s | Runs well |
| 69Good quality (B) · 69 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. | InternVL3 38B | Q6_K | 52.7 GB | 1.2 tok/s | Very slow |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning (14B) | Q6_K | 32.7 GB | 3.2 tok/s | Slow |
| 52Fair quality (C) · 52 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. | Qwen1.5 110B Chat | Q8_0 | 140 GB | 0.3 tok/s | Very slow |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Vision 15B | Q6_K | 33.1 GB | 3.1 tok/s | Slow |
| 54Fair quality (C) · 54 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. | Groot 19B A3B 261023 | Q4_K_M | 31.1 GB | 21.2 tok/s | Runs well |
| 66Good quality (B) · 66 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. | Nanbeige4.3 33B | Q2_K | 34.0 GB | 3.4 tok/s | Slow |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q4_K_M | 21.9 GB | 16.3 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q4_K_M | 22.1 GB | 14.7 tok/s | Runs well |
| 67Good quality (B) · 67 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. | Qwen3 14B | Q6_K | 32.5 GB | 3.2 tok/s | Slow |
| 52Fair quality (C) · 52 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. | Sarvam 105B | Q2_K | 61.7 GB | 10.9 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q4_K_M | 20.3 GB | 35.7 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. | Grok-1 (314B) | Q4_K_M | 213 GB | 0.8 tok/s | Very slowtight fit |
| 49Fair quality (C) · 49 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. | DeepSeek Coder V2 Lite (16B) | Q4_K_M | 28.9 GB | 26.1 tok/s | Runs well |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q8_0 | 23.1 GB | 47.7 tok/s | Runs great |
| 43Fair quality (C) · 43 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. | Granite 4.0 H Tiny (7B-A1B) | Q6_K | 24.8 GB | 40.6 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 62/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 22.1 GB | 15.1 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL-Cowork 4.7B | Q4_K_M | 23.1 GB | 14.5 tok/s | Runs well |
| 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. | Ministral 3 14B Reasoning | Q6_K | 31.8 GB | 3.4 tok/s | Slow |
| 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. | AceReason Nemotron 14B | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 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. | OpenReasoning Nemotron 14B | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 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. | Qwen2.5 Coder 14B Instruct | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 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. | Apriel Nemotron 15B Thinker | Q6_K | 33.0 GB | 3.2 tok/s | Slow |
| 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. | Hermes 4 14B | Q6_K | 32.5 GB | 3.2 tok/s | Slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Muse Glimmer 30B | Q2_K | 31.1 GB | 3.8 tok/s | Slow |
| 59Good quality (B) · 59 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. | Apertus 70B Instruct | Q6_K | 79.6 GB | 0.7 tok/s | Very slow |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2 (24B) | Q3_K_M | 32.1 GB | 3.7 tok/s | Slow |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 31B | Q2_K | 33.2 GB | 3.6 tok/s | Slow |
| 63Good quality (B) · 63 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. | Granite 4.2 30B | Q3_K_M | 35.5 GB | 3.0 tok/s | Slow |
| 55Good quality (B) · 55 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. | Fara 1.5 4B | Q4_K_M | 22.1 GB | 15.1 tok/s | Runs well |
| 63Good quality (B) · 63 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. | Ministral 3 14B | Q6_K | 31.8 GB | 3.4 tok/s | Slow |
| 63Good quality (B) · 63 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. | Phi-4 (14B) | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 63Good quality (B) · 63 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. | DeepCoder 14B Preview | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 63Good quality (B) · 63 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. | InternVL3 14B | Q6_K | 33.0 GB | 3.1 tok/s | Slow |
| 53Fair quality (C) · 53 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. | Phi-3.5 MoE (42B-A6.6B) | Q4_K_M | 45.6 GB | 10.0 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Thinking 2507 | Q4_K_M | 22.7 GB | 17.1 tok/s | Runs well |
| 56Good quality (B) · 56 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. | K2 Horizon 7B | Q2_K | 23.8 GB | 12.5 tok/s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Reka Flash 3.1 (21B) | Q4_K_M | 32.9 GB | 3.3 tok/s | Slow |
| 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. | Snowflake Arctic Instruct | Q2_K | 211 GB | 6.5 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 72B Instruct | Q6_K | 80.0 GB | 0.7 tok/s | Very slow |
| 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 70B Instruct | Q6_K | 79.6 GB | 0.7 tok/s | Very slow |
| 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. | PaddleOCR-VL 1.6 0.9B | Q6_K | 20.0 GB | 49.6 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 8B | Q3_K_M | 24.7 GB | 10.1 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q5_K_M | 20.1 GB | 43.6 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. | Unlimited OCR (3B-A0.6B) | Q8_0 | 23.1 GB | 47.7 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. | Mage-VL 4.7B | Q4_K_M | 23.1 GB | 14.5 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Instruct | Q4_K_M | 29.3 GB | 21.2 tok/s | Runs well |
| 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct | Q6_K | 32.7 GB | 3.2 tok/s | Slow |
| 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 14B | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 51Fair quality (C) · 51 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. | Qwen3 4B Instruct 2507 | Q4_K_M | 22.7 GB | 17.1 tok/s | Runs well |
| 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | JanusCoder 14B | Q6_K | 32.5 GB | 3.2 tok/s | Slow |
| 54Fair quality (C) · 54 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. | MiMo V2.6 Distill Qwen 9B | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 54Fair quality (C) · 54 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. | SenseNova Loop 9B Preview | Q2_K | 23.4 GB | 11.7 tok/s | Runs well |
| 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. | Magistral Small 1.2 (24B) | Q3_K_M | 32.1 GB | 3.7 tok/s | Slow |
| 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. | Granite 4.1 30B | Q3_K_M | 35.3 GB | 3.1 tok/s | Slow |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 27B IT | Q3_K_M | 33.3 GB | 3.2 tok/s | Slow |
| 51Fair quality (C) · 51 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. | Qwen3-VL 4B Instruct | Q4_K_M | 22.9 GB | 15.5 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 3B | Q4_K_M | 21.9 GB | 18.7 tok/s | Runs well |
| 53Fair quality (C) · 53 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. | Ornith 1.5 9B | Q2_K | 23.2 GB | 11.7 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | TeleOCR | Q5_K_M | 21.0 GB | 39.9 tok/s | Runs great |
| 59Good quality (B) · 59 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. | Gemma 3 12B IT | Q6_K | 29.7 GB | 3.9 tok/s | Slow |
| 53Fair quality (C) · 53 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. | Qwen3.5 9B | Q2_K | 23.2 GB | 11.7 tok/s | Runs well |
| 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct 1M | Q6_K | 32.8 GB | 3.2 tok/s | Slow |
| 58Good quality (B) · 58 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. | Devstral Small 1.1 (24B) | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 58Good quality (B) · 58 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. | Magistral Small 2507 | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Codestral 22B | Q4_K_M | 34.5 GB | 3.1 tok/s | Slow |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | Q4_K_M | 20.1 GB | 44.3 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 59/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 27B Text IT | Q3_K_M | 33.1 GB | 3.3 tok/s | Slow |
| 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. | Ornith 1.0 9B | Q2_K | 23.2 GB | 11.7 tok/s | Runs well |
| 51Fair quality (C) · 51 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. | TMax 9B | Q2_K | 22.9 GB | 12.6 tok/s | Runs well |
| 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. | DeepSeek R1 0528 Qwen3 8B | Q3_K_M | 24.3 GB | 10.8 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 8B-A1B | Q4_K_M | 24.2 GB | 39.6 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mixtral 8x7B DPO | Q6_K | 58.4 GB | 3.6 tok/s | Slow |
| 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. | InternVL3.5 8B | Q3_K_M | 24.4 GB | 10.4 tok/s | Runs well |
| 57Good quality (B) · 57 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. | Magistral Small 2506 | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 43Fair quality (C) · 43 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. | Moonlight 16B-A3B Instruct | Q4_K_M | 29.0 GB | 21.2 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.5 33B | Q2_K | 33.5 GB | 3.3 tok/s | Slow |
| 57Good quality (B) · 57 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. | Mistral Small 3.2 24B | Q3_K_M | 32.1 GB | 3.7 tok/s | Slow |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q4_K_M | 20.3 GB | 36.5 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. | Qwen3 4B | Q4_K_M | 22.7 GB | 17.1 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | North Micro Vision | Q4_K_M | 21.5 GB | 27.7 tok/s | Runs well |
| 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. | Qwen3-VL 8B Instruct | Q3_K_M | 24.5 GB | 10.1 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 4B | Q4_K_M | 21.6 GB | 17.3 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 57B-A14B Instruct | Q6_K | 66.6 GB | 3.4 tok/s | Slow |
| 57Good quality (B) · 57 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. | Terminal RSI 27B | Q3_K_M | 33.2 GB | 3.2 tok/s | Slow |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Solar Pro Preview 22B | Q4_K_M | 33.9 GB | 3.1 tok/s | Slow |
| 35Basic quality (D) · 35 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. | MiniCPM5 1B | Q6_K | 20.1 GB | 44.1 tok/s | Runs great |
| 56Good quality (B) · 56 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. | Seed-OSS 36B Instruct | Q2_K | 35.6 GB | 3.1 tok/s | Slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 8B | Q3_K_M | 24.3 GB | 10.8 tok/s | Runs well |
| 56Good quality (B) · 56 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. | Hemmingway 1.5 | Q3_K_M | 32.7 GB | 3.3 tok/s | Slow |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | Q4_K_M | 20.8 GB | 25.4 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2505 | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.1 24B | Q3_K_M | 32.1 GB | 3.7 tok/s | Slow |
| 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. | Qianfan-OCR 4B | Q4_K_M | 23.1 GB | 14.5 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.5 8B | Q3_K_M | 24.5 GB | 10.2 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 8B | Q3_K_M | 24.7 GB | 10.1 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x7B Instruct | Q6_K | 58.4 GB | 3.6 tok/s | Slow |
| 55Good quality (B) · 55 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. | Hermes 4.3 36B | Q2_K | 35.6 GB | 3.1 tok/s | Slow |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 9B | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | UI-Venus 2 9B | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova 6.8 Code2Video | Q3_K_M | 33.0 GB | 3.2 tok/s | Slow |
| 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. | Granite 4.1 3B | Q4_K_M | 21.8 GB | 20.2 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 22B V2 | Q4_K_M | 34.5 GB | 3.1 tok/s | Slow |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 32B Instruct | Q2_K | 34.5 GB | 3.4 tok/s | Slow |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 2B | Q4_K_M | 20.5 GB | 30.2 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 57/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Reasoning | Q3_K_M | 24.1 GB | 10.8 tok/s | Runs well |
| 48Fair quality (C) · 48 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. | MiMo-VL 7B RL | Q3_K_M | 24.3 GB | 10.7 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Lite Chat | Q4_K_M | 28.9 GB | 26.1 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Mini | Q4_K_M | 50.6 GB | 5.6 tok/s | Slow |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5-VL 3B | Q4_K_M | 21.1 GB | 22.0 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3 24B (2501) | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 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. | LightOnOCR-3 4B | Q4_K_M | 22.1 GB | 15.1 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini Reasoning (3.8B) | Q4_K_M | 22.4 GB | 17.9 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Jamba Reasoning 3B | Q4_K_M | 21.0 GB | 21.4 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E4B | Q4_K_M | 24.0 GB | 17.2 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Skywork OR1 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Think | Q2_K | 32.7 GB | 3.5 tok/s | Slow |
| 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. | Falcon-H1R 7B | Q3_K_M | 23.1 GB | 11.7 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | MiMo 7B RL | Q3_K_M | 24.1 GB | 11.3 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 7.8B | Q3_K_M | 23.9 GB | 11.3 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E2B | Q4_K_M | 22.5 GB | 34.3 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 56/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 8B | Q3_K_M | 23.4 GB | 11.2 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 180B Chat | Q6_K | 167 GB | 0.3 tok/s | Very slow |
| 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. | Seed-Coder 8B Instruct | Q3_K_M | 24.1 GB | 10.8 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Jamba2 3B | Q4_K_M | 20.9 GB | 22.6 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Chandra OCR 2 | Q4_K_M | 22.5 GB | 12.9 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM3 3B | Q4_K_M | 21.5 GB | 22.3 tok/s | Runs well |
| 31Basic quality (D) · 31 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q6_K | 20.1 GB | 40.7 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 56/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin Mistral 24B Venice Edition | Q3_K_M | 32.1 GB | 3.7 tok/s | Slow |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 7B Instruct | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Small 24B | Q3_K_M | 32.3 GB | 3.7 tok/s | Slow |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 32B | Q2_K | 34.0 GB | 3.5 tok/s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 27B IT | Q3_K_M | 34.1 GB | 3.3 tok/s | Slow |
| 45Fair quality (C) · 45 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. | Olmo 3 7B Think | Q3_K_M | 24.1 GB | 12.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini (3.8B) | Q4_K_M | 22.4 GB | 17.9 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 3B | Q4_K_M | 22.3 GB | 17.8 tok/s | Runs well |
| 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. | GLM-4 32B 0414 | Q2_K | 32.6 GB | 3.5 tok/s | Slow |
| 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. | GLM-Z1 32B (0414) | Q2_K | 32.6 GB | 3.5 tok/s | Slow |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 2B Instruct | Q4_K_M | 21.3 GB | 32.2 tok/s | Runs great |
| 43Fair quality (C) · 43 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. | Granite 4.0 H Small (32B-A9B) | Q2_K | 32.1 GB | 12.1 tok/s | Runs well |
| 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. | Gemma 3 4B IT | Q4_K_M | 21.9 GB | 16.0 tok/s | Runs well |
| 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. | OpenReasoning Nemotron 7B | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 22B (2409) | Q4_K_M | 34.5 GB | 3.1 tok/s | Slow |
| 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. | Llama 3.1 Nemotron Nano 8B v1 | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Nemo 12B Instruct | Q4_K_M | 27.8 GB | 5.6 tok/s | Slow |
| 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. | MiniCPM4 8B | Q3_K_M | 23.3 GB | 10.8 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 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. | WeVisOne-VL 4B | Q4_K_M | 23.2 GB | 14.2 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 R1 Mistral 24B | Q3_K_M | 31.9 GB | 3.8 tok/s | Slow |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 4B IT | Q4_K_M | 21.9 GB | 16.0 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 32B | Q2_K | 32.6 GB | 3.5 tok/s | Slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Instruct | Q2_K | 32.7 GB | 3.5 tok/s | Slow |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 4B v1.1 | Q4_K_M | 22.9 GB | 15.2 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 7B Instruct | Q3_K_M | 23.8 GB | 11.8 tok/s | Runs well |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 1.2B | Q5_K_M | 20.4 GB | 44.3 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 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 8B Reasoning | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 Micro (3B) | Q4_K_M | 21.8 GB | 20.2 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan M2 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | OpenHands LM 32B | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 32B Instruct | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 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. | Hunyuan 4B Instruct | Q4_K_M | 22.8 GB | 16.3 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 7B Instruct | Q3_K_M | 23.6 GB | 10.7 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral 12B (2409) | Q4_K_M | 27.9 GB | 5.5 tok/s | Slow |
| 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. | MiniCPM-o 2.6 8B | Q3_K_M | 23.8 GB | 10.2 tok/s | Runs well |
| 42Fair quality (C) · 42 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. | Nemotron Nano 9B v2 | Q2_K | 22.7 GB | 12.7 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Mini Instruct | Q4_K_M | 24.6 GB | 18.0 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Instruct | Q3_K_M | 24.1 GB | 12.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Multimodal Instruct | Q4_K_M | 23.5 GB | 12.3 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Micro | Q4_K_M | 21.0 GB | 21.5 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 7B Instruct | Q3_K_M | 23.1 GB | 11.7 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct 1M | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 70B Instruct | Q6_K | 76.9 GB | 0.7 tok/s | Very slow |
| 47Fair quality (C) · 47 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. | Qwen2.5-VL 32B Instruct | Q2_K | 34.6 GB | 3.4 tok/s | Slow |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 1.1 8B Instruct | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2.5 8B | Q3_K_M | 24.1 GB | 11.0 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 9B | Q3_K_M | 23.2 GB | 11.2 tok/s | Runs well |
| 42Fair quality (C) · 42 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. | GLM-4.1V 9B Thinking | Q2_K | 23.5 GB | 11.0 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 20B Chat | Q4_K_M | 32.8 GB | 3.5 tok/s | Slow |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Fara 7B | Q3_K_M | 23.6 GB | 10.7 tok/s | Runs well |
| 27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 1B | Q5_K_M | 20.1 GB | 38.8 tok/s | Runs great |
| 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. | Qwen2.5 Coder 32B Instruct | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 2.6B | Q4_K_M | 20.7 GB | 26.7 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | InternLM3 8B Instruct | Q3_K_M | 23.7 GB | 10.1 tok/s | Runs well |
| 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. | GLM-Z1 9B (0414) | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 1.7B | Q4_K_M | 21.2 GB | 33.8 tok/s | Runs great |
| 26Basic quality (D) · 26 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. | Qwen3.5 0.8B | Q8_0 | 20.1 GB | 40.2 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 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 3B Instruct | Q4_K_M | 21.2 GB | 22.2 tok/s | Runs well |
| 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. | QwQ 32B Preview | Q2_K | 34.3 GB | 3.4 tok/s | Slow |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 1.2B | Q6_K | 20.1 GB | 40.7 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. | Falcon-H1 3B Instruct | Q4_K_M | 21.2 GB | 21.8 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | OLMoE 1B-7B Instruct | Q4_K_M | 23.8 GB | 44.8 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 53/100 (quality, fit, speed and memory use) sets the ranking. | AFM 4.5B | Q4_K_M | 22.5 GB | 14.9 tok/s | Runs well |
| 39Basic quality (D) · 39 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. | Ministral 3 8B | Q2_K | 23.7 GB | 12.6 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 8B) | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 8B Instruct | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Vision Instruct | Q4_K_M | 24.8 GB | 16.5 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 2.6 8B | Q3_K_M | 23.5 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM3 4B | Q4_K_M | 21.8 GB | 16.9 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 1.5B Instruct | Q4_K_M | 20.2 GB | 44.6 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. | Falcon-H1 1.5B Instruct | Q4_K_M | 20.2 GB | 44.3 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 53/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 3B Instruct | Q4_K_M | 21.9 GB | 21.4 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 7B Instruct | Q3_K_M | 23.6 GB | 11.9 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 128K Instruct | Q4_K_M | 24.6 GB | 18.0 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | DeepScaleR 1.5B Preview | Q4_K_M | 20.4 GB | 38.6 tok/s | Runs great |
| 44Fair quality (C) · 44 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. | Falcon-H1 34B Instruct | Q2_K | 33.7 GB | 3.4 tok/s | Slow |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium 128K Instruct | Q4_K_M | 29.2 GB | 4.9 tok/s | Slow |
| 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. | Qwen2.5 3B Instruct | Q4_K_M | 21.2 GB | 22.2 tok/s | Runs well |
| 25Basic quality (D) · 25 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. | EXAONE 3.5 2.4B | Q3_K_M | 20.8 GB | 36.8 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. | DeepSeek R1 Distill Qwen 7B | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 7.8B | Q3_K_M | 23.9 GB | 11.3 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium (14B) | Q4_K_M | 28.4 GB | 4.9 tok/s | Slow |
| 34Basic quality (D) · 34 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. | Phi-3 Mini 4K Instruct | Q4_K_M | 23.0 GB | 18.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 8B (2410) | Q3_K_M | 24.2 GB | 11.1 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | DeepHermes 3 Llama 3 8B Preview | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 Llama 3.1 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 8B Instruct | Q3_K_M | 24.4 GB | 10.9 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 8B | Q3_K_M | 24.4 GB | 10.9 tok/s | Runs well |
| 25Basic quality (D) · 25 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. | Granite 3.2 2B Instruct | Q3_K_M | 20.9 GB | 35.1 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 52/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 2B | Q3_K_M | 20.9 GB | 35.1 tok/s | Runs great |
| 39Basic quality (D) · 39 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. | DeepSeek LLM 67B Chat | Q6_K | 75.9 GB | 0.7 tok/s | Very slow |
| 43Fair quality (C) · 43 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. | Command R (08-2024) 32B | Q2_K | 33.3 GB | 3.5 tok/s | Slow |
| 22Basic quality (D) · 22 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. | Qwen2.5 1.5B Instruct | Q4_K_M | 20.2 GB | 44.6 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 52/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 1.6B | Q4_K_M | 20.1 GB | 43.4 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 52/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Small 8K Instruct | Q3_K_M | 23.7 GB | 12.0 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 13B Instruct | Q4_K_M | 30.8 GB | 5.0 tok/s | Slow |
| 35Basic quality (D) · 35 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. | S5 nano | Q4_K_M | 22.1 GB | 14.7 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Qwen2 7B Instruct | Q3_K_M | 23.2 GB | 11.6 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Dolphin 2.9.4 Llama 3.1 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Hermes 2 Pro Llama 3 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | OpenChat 3.6 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B 0414 | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | InternVL2 8B | Q3_K_M | 24.1 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Nano | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Granite 3.1 8B Instruct | Q3_K_M | 24.4 GB | 10.9 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Command R7B | Q3_K_M | 23.3 GB | 11.0 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 3B Instruct | Q4_K_M | 21.6 GB | 18.3 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 Llama 3.2 3B | Q4_K_M | 21.9 GB | 21.4 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Mini 3B | Q4_K_M | 22.9 GB | 14.7 tok/s | Runs well |
| 36Basic quality (D) · 36 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. | Qwen2-VL 7B Instruct | Q3_K_M | 23.6 GB | 10.7 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 2B Instruct | Q3_K_M | 20.9 GB | 35.1 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 10B Instruct | Q2_K | 24.5 GB | 10.9 tok/s | Runs well |
| 42Fair quality (C) · 42 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. | Aya Expanse 32B | Q2_K | 33.3 GB | 3.5 tok/s | Slow |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Vision 128K Instruct | Q4_K_M | 24.8 GB | 16.5 tok/s | Runs well |
| 42Fair quality (C) · 42 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. | Aya Vision 32B | Q2_K | 33.6 GB | 3.4 tok/s | Slow |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 32B Instruct | Q2_K | 33.0 GB | 3.5 tok/s | Slow |
| 22Basic quality (D) · 22 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. | WeVisOne VL 2B | Q3_K_M | 21.2 GB | 36.4 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 1B Instruct | Q5_K_M | 20.2 GB | 45.7 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 8B | Q3_K_M | 23.6 GB | 10.3 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 2B | Q3_K_M | 20.8 GB | 34.0 tok/s | Runs great |
| 35Basic quality (D) · 35 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. | Gemma 2 9B IT | Q2_K | 24.3 GB | 12.2 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Prover V2 7B | Q3_K_M | 26.4 GB | 12.8 tok/s | Runs well |
| 20Basic quality (D) · 20 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. | DeepSeek R1 Distill Qwen 1.5B | Q4_K_M | 20.4 GB | 38.6 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 8B Instruct | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 20Basic quality (D) · 20 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. | Hunyuan 1.8B Instruct | Q4_K_M | 20.7 GB | 38.3 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 51/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM2 2.2B Instruct | Q3_K_M | 21.7 GB | 39.4 tok/s | Runs great |
| 19Basic quality (D) · 19 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. | Granite 3.1 3B-A800M Instruct | Q6_K | 22.3 GB | 49.0 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 2B Instruct | Q3_K_M | 20.3 GB | 40.1 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B Arabic | Q3_K_M | 23.3 GB | 11.0 tok/s | Runs well |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Mistral-NeMo-Minitron 8B Instruct | Q3_K_M | 24.5 GB | 10.5 tok/s | Runs well |
| 25Basic quality (D) · 25 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. | Falcon 3 3B Instruct | Q3_K_M | 21.4 GB | 27.5 tok/s | Runs well |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 1B | Q6_K | 19.9 GB | 47.6 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. | SmolLM2 1.7B Instruct | Q4_K_M | 21.7 GB | 40.1 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 70B Chat | Q6_K | 76.9 GB | 0.7 tok/s | Very slow |
| 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. | Granite 3.0 2B Instruct | Q3_K_M | 20.7 GB | 33.7 tok/s | Runs great |
| 33Basic quality (D) · 33 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. | GLM-4 9B Chat 1M | Q2_K | 23.5 GB | 11.9 tok/s | Runs well |
| 37Basic quality (D) · 37 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. | Command R 35B (v01) | Q2_K | 43.8 GB | 3.2 tok/s | Slow |
| 33Basic quality (D) · 33 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. | GLM-4 9B Chat (2024) | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Chat 20B | Q4_K_M | 32.8 GB | 3.5 tok/s | Slow |
| 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. | Qwen2.5-Math 1.5B Instruct | Q4_K_M | 20.1 GB | 44.6 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. | InternLM2.5 7B Chat | Q3_K_M | 23.9 GB | 11.5 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 8B Instruct | Q3_K_M | 24.1 GB | 11.0 tok/s | Runs well |
| 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. | SmolVLM 2.2B Instruct | Q3_K_M | 21.7 GB | 39.4 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 50/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek MoE 16B Chat | Q3_K_M | 28.0 GB | 28.7 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 8B Instruct | Q3_K_M | 23.7 GB | 10.9 tok/s | Runs well |
| 32Basic quality (D) · 32 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. | Apertus v1.5 8B | Q2_K | 23.7 GB | 12.7 tok/s | Runs well |
| 17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 3B-A800M Instruct | Q6_K | 22.1 GB | 49.0 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. | d1 2B | Q4_K_M | 20.3 GB | 35.7 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | LFM2 700M | Q8_0 | 19.9 GB | 47.2 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 50/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 9B Chat | Q3_K_M | 24.2 GB | 10.0 tok/s | Runs well |
| 31Basic quality (D) · 31 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. | Mistral 7B Instruct v0.3 | Q3_K_M | 23.7 GB | 12.2 tok/s | Runs well |
| 32Basic quality (D) · 32 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. | CodeGeeX4 All 9B | Q2_K | 23.1 GB | 12.0 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B Instruct | Q4_K_M | 29.4 GB | 4.3 tok/s | Slow |
| 31Basic quality (D) · 31 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. | Zamba2 7B Instruct | Q3_K_M | 23.4 GB | 12.1 tok/s | Runs well |
| 31Basic quality (D) · 31 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. | Falcon3 Mamba 7B Instruct | Q3_K_M | 22.6 GB | 12.2 tok/s | Runs well |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Granite Vision 3.2 2B | Q2_K | 20.9 GB | 37.8 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 49/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 6.7B Instruct | Q4_K_M | 27.4 GB | 10.2 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 20B | Q4_K_M | 32.8 GB | 3.5 tok/s | Slow |
| 20Basic quality (D) · 20 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. | Qwen1.5 MoE A2.7B Chat | Q3_K_M | 27.7 GB | 29.7 tok/s | Runs well |
| 31Basic quality (D) · 31 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. | EXAONE 3.0 7.8B Instruct | Q3_K_M | 23.4 GB | 11.3 tok/s | Runs well |
| 31Basic quality (D) · 31 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. | Dolphin 2.9 Llama 3 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 7B | Q2_K | 23.8 GB | 10.5 tok/s | Runs well |
| 35Basic quality (D) · 35 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. | Aya 23 35B | Q2_K | 43.8 GB | 3.2 tok/s | Slow |
| 30Basic quality (D) · 30 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. | OLMo 2 7B Instruct | Q3_K_M | 24.8 GB | 12.2 tok/s | Runs well |
| 31Basic quality (D) · 31 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. | LLM4Decompile 9B V2 | Q3_K_M | 24.2 GB | 10.0 tok/s | Runs well |
| 30Basic quality (D) · 30 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. | Hermes 2 Pro Mistral 7B | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 30Basic quality (D) · 30 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. | Starling LM 7B Beta | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | CogVLM2 Llama 3 Chat 19B | Q4_K_M | 35.2 GB | 3.5 tok/s | Slow |
| 30Basic quality (D) · 30 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. | Codestral Mamba 7B | Q3_K_M | 22.6 GB | 12.2 tok/s | Runs well |
| 17Basic quality (D) · 17 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. | InternLM2.5 1.8B Chat | Q4_K_M | 21.0 GB | 36.3 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 49/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 2.7B Instruct | Q3_K_M | 20.7 GB | 33.4 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 49/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 7B Instruct | Q3_K_M | 23.0 GB | 11.6 tok/s | Runs well |
| 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. | Yi Coder 1.5B Chat | Q4_K_M | 21.5 GB | 46.4 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 48/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 6.7B V2 | Q4_K_M | 27.4 GB | 10.2 tok/s | Runs well |
| 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. | Falcon 3 1B Instruct | Q4_K_M | 20.7 GB | 41.1 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 48/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (0106) | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 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. | Qwen2 1.5B Instruct | Q4_K_M | 20.2 GB | 44.6 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 48/100 (quality, fit, speed and memory use) sets the ranking. | Spark X2.6 1.7B | Q4_K_M | 20.2 GB | 40.1 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. | surya ocr 2.5 | Q8_0 | 19.9 GB | 50.6 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | GLiDE 2B | Q4_K_M | 20.3 GB | 36.5 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. | Stable Code Instruct 3B | Q2_K | 22.8 GB | 40.3 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. | Mistral 7B Instruct v0.2 | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mistral 7B DPO | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (1210) | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Mathstral 7B | Q3_K_M | 23.7 GB | 12.2 tok/s | Runs well |
| 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. | Yi 1.5 9B Chat | Q3_K_M | 23.8 GB | 10.0 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 3B | Q4_K_M | 22.7 GB | 12.4 tok/s | Runs well |
| 35Basic quality (D) · 35 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. | Yi 1.5 34B Chat | Q2_K | 33.8 GB | 3.3 tok/s | Slow |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 11B Vision Instruct | Q2_K | 24.6 GB | 10.6 tok/s | Runs well |
| 14Basic quality (D) · 14 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. | Qwen3 0.6B | Q8_0 | 20.8 GB | 46.6 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | LFM2.5 350M | F16 | 19.8 GB | 46.0 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | Falcon-H1 0.5B Instruct | Q8_0 | 19.7 GB | 67.2 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 48/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 14B Chat | Q4_K_M | 34.4 GB | 4.8 tok/s | Slow |
| 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. | CodeGemma 7B | Q3_K_M | 27.0 GB | 10.4 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 8B | Q3_K_M | 24.0 GB | 11.0 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | SQLCoder 7B v2 | Q4_K_M | 27.4 GB | 10.2 tok/s | Runs well |
| 13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 1.7B Instruct | Q4_K_M | 20.5 GB | 40.1 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 48/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 1B Instruct | Q4_K_M | 20.5 GB | 46.4 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. | Granite Code 20B Instruct | Q4_K_M | 31.5 GB | 3.4 tok/s | Slow |
| 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. | OpenHermes 2.5 Mistral 7B | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 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. | Starling LM 7B Alpha | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 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. | Nous Hermes 2 SOLAR 10.7B | Q2_K | 24.1 GB | 10.5 tok/s | Runs well |
| 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. | SOLAR 10.7B Instruct | Q2_K | 24.1 GB | 10.5 tok/s | Runs well |
| 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. | InternLM2 Math Plus 7B | Q3_K_M | 23.9 GB | 11.5 tok/s | Runs well |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 1.3B Instruct | Q5_K_M | 21.6 GB | 42.0 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. | LLM4Decompile 1.3B V2 | Q5_K_M | 21.6 GB | 42.0 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. | Granite Code 8B Instruct (128K) | Q3_K_M | 24.2 GB | 11.0 tok/s | Runs well |
| 12Basic quality (D) · 12 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. | LFM2 350M | F16 | 19.8 GB | 46.0 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | Granite 4.0 H 350M | F16 | 19.7 GB | 47.4 tok/s | Runs great |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 450M | Q8_0 | 19.6 GB | 77.6 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 47/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 6B Chat | Q4_K_M | 23.0 GB | 11.3 tok/s | Runs well |
| 11Basic quality (D) · 11 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. | StableLM Zephyr 3B | Q2_K | 21.5 GB | 40.3 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | StarCoder2 3B | Q2_K | 20.5 GB | 37.2 tok/s | Runs great |
| 11Basic quality (D) · 11 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. | Phi-2 2.7B | Q2_K | 20.8 GB | 40.5 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | Granite Code 3B Instruct (128K) | Q2_K | 23.1 GB | 32.4 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 47/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.1 | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 0.8B | Q8_0 | 19.9 GB | 46.6 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 46/100 (quality, fit, speed and memory use) sets the ranking. | Falcon Mamba 7B Instruct | Q3_K_M | 22.6 GB | 12.2 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 32B Chat | Q2_K | 34.2 GB | 3.5 tok/s | Slow |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 33B Instruct | Q2_K | 34.4 GB | 3.4 tok/s | Slow |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 13B Instruct | Q4_K_M | 33.7 GB | 5.3 tok/s | Slow |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B (base) | Q4_K_M | 29.4 GB | 4.3 tok/s | Slow |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 34B | Q2_K | 33.9 GB | 3.2 tok/s | Slow |
| 10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 500M Instruct | Q8_0 | 19.9 GB | 68.5 tok/s | Runs great |
| 10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 0.5B Instruct | Q8_0 | 19.7 GB | 71.3 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | LFM2.5 230M | F16 | 19.6 GB | 70.0 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. | CodeGemma 2B | Q2_K | 20.2 GB | 44.9 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 46/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 1.6B Chat | Q4_K_M | 20.8 GB | 41.8 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 46/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 Zephyr 1.6B | Q4_K_M | 20.8 GB | 41.8 tok/s | Runs great |
| 15Basic quality (D) · 15 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. | Nemotron Mini 4B Instruct | Q2_K | 21.2 GB | 26.9 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Neural Chat 7B v3.3 | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | RecurrentGemma 9B IT | Q2_K | 23.0 GB | 11.7 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 Mistral 7B | Q3_K_M | 23.8 GB | 11.7 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 1.1 7B IT | Q3_K_M | 27.0 GB | 10.4 tok/s | Runs well |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2B IT | Q2_K | 20.2 GB | 44.9 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. | Hunyuan 0.5B Instruct | Q8_0 | 20.4 GB | 64.7 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 360M Instruct | F16 | 20.1 GB | 44.7 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. | Qwen1.5 7B Chat | Q3_K_M | 27.1 GB | 11.5 tok/s | Runs well |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 7B Instruct | Q4_K_M | 27.4 GB | 10.2 tok/s | Runs well |
| 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. | Qwen2.5 Coder 0.5B Instruct | Q8_0 | 19.7 GB | 71.3 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. | WizardMath 7B v1.1 | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Zephyr 7B Beta | Q3_K_M | 23.7 GB | 12.3 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 13B | Q4_K_M | 30.3 GB | 5.3 tok/s | Slow |
| 26Basic quality (D) · 26 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. | StableLM 2 12B Chat | Q4_K_M | 27.3 GB | 5.7 tok/s | Slow |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Yi 34B Chat | Q2_K | 33.8 GB | 3.3 tok/s | Slow |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 34B Instruct | Q2_K | 32.9 GB | 3.3 tok/s | Slow |
| 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. | Gemma 7B IT | Q3_K_M | 27.0 GB | 10.4 tok/s | Runs well |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 7B | Q3_K_M | 23.1 GB | 12.4 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 34B Instruct | Q2_K | 34.1 GB | 3.3 tok/s | Slow |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 0.3B | F16 | 19.9 GB | 44.7 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 256M Instruct | F16 | 19.7 GB | 61.9 tok/s | Runs great |
| 5Basic quality (D) · 5 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | TinyLlama 1.1B Chat | Q6_K | 20.0 GB | 43.3 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 0.5B Instruct | Q8_0 | 19.7 GB | 71.3 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 270M | F16 | 19.6 GB | 59.6 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 44/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 13B Chat | Q4_K_M | 30.3 GB | 5.3 tok/s | Slow |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 7B | Q4_K_M | 25.3 GB | 10.2 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 13B Chat | Q4_K_M | 30.9 GB | 4.9 tok/s | Slow |
| 5Basic quality (D) · 5 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 360M Instruct | F16 | 19.8 GB | 44.7 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. | StarCoder 15B | Q4_K_M | 28.8 GB | 4.3 tok/s | Slow |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | Yi 6B Chat | Q3_K_M | 22.3 GB | 14.6 tok/s | Runs well |
| 4Basic quality (D) · 4 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 135M Instruct | F16 | 19.5 GB | 124 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 43/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 7B Chat | Q3_K_M | 24.5 GB | 13.2 tok/s | Runs well |
| 3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 Tiny 90M Instruct | F16 | 19.3 GB | 179 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 43/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 7B Chat | Q3_K_M | 24.9 GB | 11.8 tok/s | Runs well |
| 20Basic quality (D) · 20 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. | WizardLM 13B v1.2 | Q4_K_M | 30.3 GB | 5.3 tok/s | Slow |
| 20Basic quality (D) · 20 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. | LLaVA 1.5 13B | Q4_K_M | 30.5 GB | 5.1 tok/s | Slow |
| 2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 135M Instruct | F16 | 19.3 GB | 124 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 42/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek LLM 7B Chat | Q3_K_M | 24.4 GB | 12.8 tok/s | Runs well |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 13B v1.5 | Q4_K_M | 30.3 GB | 5.3 tok/s | Slow |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 7B | Q2_K | 24.0 GB | 16.0 tok/s | Runs well |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 7B v1.5 | Q2_K | 23.9 GB | 16.7 tok/s | Runs well |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 7B Instruct | Q2_K | 22.9 GB | 16.4 tok/s | Runs well |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking. | InternLM 7B | Q2_K | 23.0 GB | 15.4 tok/s | Runs well |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 40B Instruct | Q4_K_M | 44.8 GB | 1.6 tok/s | Very slow |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 7B Instruct | Q2_K | 21.9 GB | 15.6 tok/s | Runs well |
| 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. | Kimi K3.1 Pro (2.8T) | Q2_K | 1,131 GB | — | 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. | DeepSeek V4.1 Flash 1017 (552B-A16B) | Q2_K | 324 GB | — | 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. | GLM-5.3 (753B-A40B) | Q2_K | 321 GB | — | 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. | Qwen3.8 Max (2.4T-A95B) | Q2_K | 998 GB | — | 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. | Kimi K3 (2.8T) | Q2_K | 1,131 GB | — | 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. | MiMo V2.6 Pro (1T-A42B) | Q2_K | 429 GB | — | 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. | Ling 3.1 Flash 1019 (560B-A25B) | Q2_K | 248 GB | — | 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. | Step 5 Preview (600B-A27B) | Q2_K | 261 GB | — | 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. | DeepSeek V4.1 Flash (552B-A16B) | Q2_K | 324 GB | — | 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. | Mistral Large 4 (1T-A52B) | Q2_K | 441 GB | — | 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. | GLM-5.2 (753B-A40B) | Q2_K | 321 GB | — | 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. | Hunyuan Hy4 Preview (780B) | Q2_K | 332 GB | — | 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. | Muse Spark Open (816B-A42B) | Q2_K | 348 GB | — | 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. | DeepSeek V4 Pro (1.6T-A49B) | Q2_K | 680 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2.6 (1T) | Q2_K | 430 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.1 Flash (560B-A25B) | Q2_K | 248 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.5 Pro (1T-A42B) | Q2_K | 429 GB | — | 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. | GLM-5.1 (744B-A40B) | Q2_K | 321 GB | — | 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. | DeepSeek V4 Pro (April 2026) | Q2_K | 659 GB | — | 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. | GLM-5 (744B-A40B) | Q2_K | 321 GB | — | 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. | Kimi K2.5 (1T) | Q2_K | 430 GB | — | 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. | Kimi K2.7 Code (1T) | Q2_K | 430 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.2 (671B) | Q2_K | 294 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Inkling (975B-A41B) | Q2_K | 400 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Ultra 550B-A55B | Q2_K | 243 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 0528 (671B) | Q2_K | 293 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Thinking (1T) | Q2_K | 430 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.2 Exp | Q2_K | 294 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 1T | Q2_K | 429 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 (671B) | Q2_K | 288 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.1 Terminus | Q2_K | 293 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.1 (671B) | Q2_K | 293 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Instruct 0905 (1T) | Q2_K | 430 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 1T | Q2_K | 422 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 3 (675B) | Q2_K | 290 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Instruct (July 2025) | Q2_K | 430 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | LongCat Flash Chat (560B) | Q2_K | 244 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3 0324 (671B) | Q2_K | 293 GB | — | Won't run |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3 (671B) | Q2_K | 288 GB | — | Won't run |
Image models on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanImage 3.0 (80B-A13B) | FP16 | 170 GB | 49.3 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP16 | 133 GB | 32.9 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | FP16 | 116 GB | 29.6 min | Very slow |
| 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. | Krea 2 Turbo | FP16 | 37.4 GB | 3.5 min | Very slow |
| 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. | Ideogram 4 | FP16 | 57.3 GB | 20.5 min | Very slow |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 49.3 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | FP16 | 63.8 GB | 74.0 min | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Ming-Image 0.1 Design | FP16 | 63.9 GB | 13.4 min | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP16 | 46.7 GB | 9.5 min | Very slow |
| 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. | Qwen-Image | FP16 | 63.8 GB | 74.0 min | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 89 s | Slow |
| 93Excellent quality (A+) · 93 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. | Fibo 2.0 Dev | FP16 | 27.7 GB | 18.5 min | Very slow |
| 87Excellent quality (A+) · 87 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. | FireRed-Image-Edit 1.1 | FP16 | 61.2 GB | 65.8 min | Very slow |
| 91Excellent quality (A+) · 91 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. | FLUX 3 Image Klein | FP16 | 22.4 GB | 4.7 min | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image-Edit 2511 | FP16 | 61.2 GB | 65.8 min | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Full | FP16 | 64.4 GB | 37.0 min | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 2.6 min | Very slow |
| 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. | ERNIE-Image | FP16 | 34.0 GB | 18.1 min | Very slow |
| 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. | Z-Image Turbo | FP16 | 22.7 GB | 2.1 min | Slow |
| 80Great quality (A) · 80 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. | HiDream-I1 Dev | FP16 | 64.4 GB | 14.0 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 49 s | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Fast | FP16 | 64.4 GB | 8.2 min | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Krea [dev] | FP16 | 36.4 GB | 9.9 min | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Kontext [dev] | FP16 | 37.0 GB | 18.1 min | Very slow |
| 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. | MOSS-Image SFT | FP16 | 29.3 GB | 11.5 min | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [dev] | FP16 | 36.4 GB | 9.9 min | Very slow |
| 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. | Z-Image | FP16 | 22.7 GB | 14.0 min | Very slow |
| 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [schnell] | FP16 | 36.4 GB | 1.6 min | Slow |
| 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. | FLUX.1 Fill [dev] | FP16 | 36.4 GB | 10.3 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Chroma1-HD | FP16 | 30.0 GB | 16.4 min | Very slow |
| 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. | CogView4 6B | FP16 | 33.9 GB | 14.8 min | Very slow |
| 62Good quality (B) · 62 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. | Stable Diffusion 3.5 Large Turbo | FP16 | 30.0 GB | 79 s | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Iris-3B | FP16 | 17.3 GB | 13.2 min | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Large | FP16 | 30.0 GB | 9.0 min | Very slow |
| 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. | SDXL Turbo | FP16 | 7.6 GB | 7.4 s | Runs great |
| 54Fair quality (C) · 54 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. | SDXL-Lightning (4-step) | FP16 | 8.9 GB | 35 s | Runs well |
| 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. | OmniGen2 | FP16 | 18.0 GB | 13.2 min | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper XL v2 Turbo | FP16 | 8.9 GB | 64 s | Slow |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Kolors | FP16 | 19.8 GB | 3.3 min | Very slow |
| 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. | Juggernaut XL v9 | FP16 | 8.9 GB | 3.7 min | Very slow |
| 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. | RealVisXL V5.0 | FP16 | 8.9 GB | 3.7 min | Very slow |
| 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. | Lumina-Image 2.0 | FP16 | 12.7 GB | 5.8 min | Very slow |
| 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. | Animagine XL 4.0 | FP16 | 8.9 GB | 3.5 min | Very slow |
| 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. | Illustrious XL v0.1 | FP16 | 8.9 GB | 3.5 min | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Medium | FP16 | 18.4 GB | 4.9 min | Very slow |
| 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Pony Diffusion V6 XL | FP16 | 8.9 GB | 3.1 min | Very slow |
| 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. | Playground v2.5 | FP16 | 8.9 GB | 6.2 min | Very slow |
| 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. | AuraFlow v0.3 | FP16 | 18.5 GB | 11.5 min | Very slow |
| 56Good quality (B) · 56 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Animagine XL 3.1 | FP16 | 8.9 GB | 3.5 min | Very slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | PixArt-Σ XL 1024 | FP16 | 12.8 GB | 74 s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3 Medium | FP16 | 17.4 GB | 2.5 min | Very slow |
| 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. | Stable Diffusion XL 1.0 | FP16 | 8.9 GB | 3.7 min | Very slow |
| 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. | SD Turbo | FP16 | 3.3 GB | 3.9 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. | Stable Cascade | FP16 | 14.0 GB | 4.1 min | Very slow |
| 30Basic quality (D) · 30 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. | LCM DreamShaper v7 | FP16 | 2.8 GB | 12 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. | Hunyuan-DiT v1.2 | FP16 | 9.3 GB | 4.9 min | Very slow |
| 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 3 | FP16 | 25.9 GB | 7.4 min | Very slow |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 2.8 GB | 59 s | Slow |
| 40Fair quality (C) · 40 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. | DreamShaper 8 | FP16 | 2.8 GB | 59 s | Slow |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 2.8 GB | 59 s | Slow |
Video models on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Image2Video (64B) | FP16 | 139 GB | 30.8 h | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP16 | 113 GB | 14.2 h | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 74.8 min | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 40.3 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 5.5 h | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 5.5 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 21.9 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 21.9 h | Very slow |
| 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. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 24.7 h | Very slow |
| 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. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 9.9 h | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Step-Video T2V (30B) | FP16 | 78.2 GB | 42.5 h | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Wan-Dancer 14B (music to dance) | FP16 | 77.0 GB | 60.3 h | Very slow |
| 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. | Wan 2.2 Animate 14B | FP16 | 65.2 GB | 26.0 h | Very slow |
| 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. | Wan 2.1 VACE 14B | FP16 | 64.6 GB | 30.1 h | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP16 | 52.5 GB | 16.4 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 T2V 14B 720P | FP16 | 60.8 GB | 32.9 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 720P | FP16 | 59.3 GB | 27.4 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 14B | FP16 | 58.0 GB | 27.4 h | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 S2V 14B (speech to video) | FP16 | 50.4 GB | 13.7 h | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP16 | 49.6 GB | 5.5 h | Very slow |
| 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. | HY-OmniWeaving (8.3B, unified video) | FP16 | 41.9 GB | 7.3 h | Very slow |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 13B | FP16 | 64.8 GB | 32.9 h | Very slow |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo I2V 13B | FP16 | 64.8 GB | 32.9 h | Very slow |
| 68Good quality (B) · 68 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. | LTX-Video 13B 0.9.8 (distilled) | FP16 | 47.9 GB | 49.3 min | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 T2V 14B 540P | FP16 | 49.0 GB | 19.2 h | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 480P | FP16 | 46.5 GB | 12.3 h | Very slow |
| 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. | Cosmos-Predict2 14B Video2World | FP16 | 57.6 GB | 21.9 h | Very slow |
| 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. | Wan 2.2 TI2V 5B | FP16 | 43.1 GB | 7.1 h | Very slow |
| 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. | Open-Sora 2.0 (11B) | FP16 | 43.8 GB | 41.1 h | Very slow |
| 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Video Lite (3B, video + audio) | FP16 | 31.5 GB | 4.2 h | Very slow |
| 60Good quality (B) · 60 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. | Cosmos 1.0 Diffusion 7B Text2World | FP16 | 48.2 GB | 7.5 h | Very slow |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 1.5 5B | FP16 | 50.3 GB | 12.3 h | Very slow |
| 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mochi 1 Preview (10B) | FP16 | 41.4 GB | 15.1 h | Very slow |
| 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. | Cosmos-Predict2 2B Video2World | FP16 | 33.6 GB | 3.4 h | Very slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP16 | 17.5 GB | 20.5 min | Slow |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP16 | 25.3 GB | 2.5 h | Very slow |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP16 | 24.1 GB | 2.5 h | Very slow |
| 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. | Wan 2.1 VACE 1.3B | FP16 | 21.5 GB | 3.6 h | Very slow |
| 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. | Wan 2.1 T2V 1.3B | FP16 | 19.8 GB | 3.3 h | Very slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Allegro (2.8B) | FP16 | 38.2 GB | 16.4 h | Very slow |
| 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. | SkyReels V2 Diffusion Forcing 1.3B | FP16 | 23.8 GB | 4.1 h | Very slow |
| 45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP16 | 17.5 GB | 49.3 min | Very slow |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 16.4 min | Slow |
Decision models on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | OpenAI Privacy Filter | F16 | 3.8 GB | 50 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 117 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. | Jina Reranker v3.5 | Q8_0 | 19.9 GB | 899 ms | Slow |
| 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 394 ms | Runs well |
| 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. | Jina Reranker v3 | Q8_0 | 19.9 GB | 899 ms | Slow |
| 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. | Qwen3 Reranker 4B | Q8_0 | 23.6 GB | 6.0 s | Very slow |
| 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. | Qwen3 Reranker 8B | Q8_0 | 28.0 GB | 12.2 s | Very slow |
| 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 656 ms | Slow |
| 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. | GLiClass Base v3 | Q8_0 | 0.8 GB | 155 ms | Runs well |
| 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. | GLiClass ModernBERT Large v3 | Q8_0 | 1.1 GB | 322 ms | Runs well |
| 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. | zerank-2 | Q8_0 | 23.6 GB | 6.0 s | Very slow |
| 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 23.9 s | Very slow |
| 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. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 449 ms | Slow |
| 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. | DeBERTa v3 Base Zero-shot v2.0 | Q8_0 | 0.8 GB | 147 ms | Runs well |
| 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. | GTE Reranker ModernBERT Base | Q8_0 | 0.8 GB | 243 ms | Runs well |
| 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. | Qwen3 Reranker 0.6B | Q8_0 | 19.9 GB | 899 ms | Slow |
| 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. | Shieldstral 1.0 3B | Q8_0 | 23.3 GB | 5.7 s | Very slow |
| 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. | DeBERTa v3 Large Zero-shot v2.0 | Q8_0 | 1.2 GB | 354 ms | Runs well |
| 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. | Intern-Decision 4B | Q8_0 | 23.9 GB | 3.5 s | Very slow |
| 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. | Granite Embedding Reranker English R2 | Q8_0 | 0.8 GB | 243 ms | Runs well |
| 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. | GLiNER2 Base v1 | Q8_0 | 0.9 GB | 171 ms | Runs well |
| 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. | mxbai-rerank-large v2 | Q8_0 | 20.7 GB | 2.3 s | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | Q8_0 | 22.4 GB | 2.4 s | Very slow |
| 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. | ModernBERT Large Zero-shot v2.0 | Q8_0 | 1.1 GB | 322 ms | Runs well |
| 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. | GLiDE 27B | Q8_0 | 34.8 GB | 20.7 s | Very slow |
| 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. | mxbai-rerank-base v2 | Q8_0 | 19.6 GB | 735 ms | Slow |
| 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. | zerank-1 small | Q8_0 | 21.1 GB | 2.6 s | Very slow |
| 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. | Skywork Reward V2 Qwen3 8B | Q8_0 | 10.5 GB | 24.1 s | Very slow |
| 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. | GLiGuard 300M | Q8_0 | 0.9 GB | 338 ms | Runs well |
| 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. | Laya | Q8_0 | 1.2 GB | 338 ms | Runs well |
| 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. | Jina Reranker v2 Base Multilingual | Q8_0 | 1.0 GB | 449 ms | Slow |
| 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. | ProtectAI DeBERTa v3 Prompt Injection v2 | Q8_0 | 0.8 GB | 290 ms | Runs well |
| 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. | LemonDecider 4B | Q8_0 | 6.5 GB | 3.6 s | Very slow |
| 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. | ms-marco MiniLM L6 v2 | F16 | 0.7 GB | 46 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. | DuoGuard 0.5B | Q8_0 | 1.2 GB | 783 ms | Slow |
| 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. | BGE Reranker v2 Gemma | Q8_0 | 21.7 GB | 3.7 s | Very slow |
| 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. | BGE Reranker v2 M3 | Q8_0 | 1.3 GB | 910 ms | Slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 8B | Q8_0 | 28.0 GB | 13.4 s | Very slow |
| 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. | Qwen3Guard Gen 4B | Q8_0 | 24.0 GB | 7.2 s | Very slow |
| 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. | Laya Multilingual | Q8_0 | 1.0 GB | 258 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. | Llama 3.1 Nemotron Safety Guard 8B v3 | Q8_0 | 27.8 GB | 13.1 s | Very slow |
| 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. | Granite Guardian 4.1 8B | Q8_0 | 28.3 GB | 13.7 s | Very slow |
| 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. | HHEM 2.1 Open | Q8_0 | 0.7 GB | 354 ms | Runs well |
| 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. | Skywork Reward V2 Qwen3 0.6B | Q8_0 | 1.4 GB | 1.9 s | Very slow |
| 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. | GLiNER Multi v2.1 | Q8_0 | 1.0 GB | 235 ms | Runs well |
| 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. | Qwen3Guard Gen 0.6B | Q8_0 | 20.1 GB | 1.2 s | Slow |
| 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. | WildGuard 7B | Q8_0 | 27.0 GB | 11.9 s | Very slow |
| 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. | Granite Guardian 3.3 8B | Q8_0 | 28.0 GB | 13.4 s | Very slow |
| 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. | NuExtract 2.0 4B | Q8_0 | 23.1 GB | 5.3 s | Very slow |
| 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. | BART Large MNLI | Q8_0 | 1.1 GB | 330 ms | Runs well |
| 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. | CompassJudger-2 32B | Q8_0 | 54.3 GB | 236.5 s | Very slow |
| 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. | NuExtract 2.0 2B | Q8_0 | 21.4 GB | 3.1 s | Very slow |
| 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. | gpt-oss-safeguard 120B | MXFP4 | 85.7 GB | 19.1 s | Very slow |
| 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. | LettuceDetect Large | Q8_0 | 1.1 GB | 1.3 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. | DynaGuard 8B | Q8_0 | 28.0 GB | 49.5 s | Very 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. | Nemotron Content Safety Reasoning 4B | Q8_0 | 23.9 GB | 26.0 s | Very 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. | Selene 1 Mini 8B | Q8_0 | 27.8 GB | 58.0 s | Very 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. | gpt-oss-safeguard 20B | MXFP4 | 31.3 GB | 13.7 s | Very slow |
| 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. | ShieldGemma 27B | Q8_0 | 48.6 GB | 40.6 s | Very slow |
| 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. | ShieldGemma 9B | Q8_0 | 29.5 GB | 13.8 s | Very 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. | CompassJudger-2 7B | Q8_0 | 27.2 GB | 55.0 s | Very slow |
| 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. | Llama Guard 3 8B | Q8_0 | 27.8 GB | 13.1 s | Very slow |
| 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. | ShieldGemma 2B | Q8_0 | 22.0 GB | 3.9 s | Very slow |
| 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. | DynaGuard 1.7B | Q8_0 | 21.4 GB | 12.3 s | Very slow |
| 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. | Prometheus 2 8x7B | Q8_0 | 68.8 GB | 93.7 s | Very slow |
| 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. | Llama Guard 4 12B | Q8_0 | 32.2 GB | 19.6 s | Very 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. | Prometheus 2 7B | Q8_0 | 27.0 GB | 52.3 s | Very slow |
| 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. | Llama Guard 3 1B | Q8_0 | 20.7 GB | 2.5 s | Very 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. | GLIDER | Q8_0 | 23.9 GB | 27.6 s | Very 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. | Flow Judge v0.1 | Q8_0 | 23.9 GB | 27.6 s | Very slow |
Upgrade picks
GPUs that would run more LLMs without offloading, at launch prices. Right now 366 of 619 LLMs run well on your Intel Xeon Silver (4100 to 4300 series) NAS (256 GB).
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.