NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) spec sheet
What the NVIDIA RTX Spark N1X (6144-core GPU) (128 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
- 128 GB
- Usable for models
- 102 GB
- Memory bandwidth
- 300 GB/s
- FP16 compute
- 28.8 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q6_K | 73.0 GB | 58.3 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q6_K | 74.3 GB | 65.1 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q6_K | 75.7 GB | 65.1 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 122B-A10B | Q4_K_M | 85.3 GB | 32.8 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 122B-A10B | Q4_K_M | 85.3 GB | 32.8 tok/s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 75.7 GB | 61.3 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 84.8 GB | 27.8 tok/s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q6_K | 75.7 GB | 65.1 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q8_0 | 46.3 GB | 50.5 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q8_0 | 51.2 GB | 58.3 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q8_0 | 46.2 GB | 50.5 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Laguna S 2.1 (118B-A8B) | Q4_K_M | 82.1 GB | 39.9 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q8_0 | 45.7 GB | 50.5 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q4_K_M | 54.5 GB | 36.0 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q8_0 | 47.1 GB | 50.5 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q3_K_M | 97.2 GB | 63.1 tok/s | Runs welltight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Super 120B-A12B | Q4_K_M | 84.3 GB | 27.8 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 90/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q4_K_M | 87.0 GB | 58.1 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q8_0 | 36.6 GB | 41.5 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 35B-A3B | Q8_0 | 46.2 GB | 50.5 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 4 (119B-A6B) | Q4_K_M | 81.8 GB | 50.9 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Qwen AgentWorld 35B-A3B | Q8_0 | 45.7 GB | 50.5 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 Flash (104B-A7.4B) | Q4_K_M | 74.4 GB | 42.6 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q8_0 | 42.3 GB | 50.5 tok/s | Runs great |
| 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Ring Flash 2.0 (100B-A6B) | Q5_K_M | 82.4 GB | 42.5 tok/s | Runs great |
| 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Ling Flash 2.0 (100B-A6B) | Q5_K_M | 82.4 GB | 42.5 tok/s | Runs great |
| 78Great quality (A) · 78 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. | GLM-4.6V | Q4_K_M | 76.0 GB | 27.8 tok/s | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy-Memory 30B-A3B | Q8_0 | 41.5 GB | 50.5 tok/s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Laguna XS 2.1 (33B-A3B) | Q8_0 | 45.6 GB | 50.5 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Linear 48B-A3B | Q8_0 | 60.9 GB | 50.5 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5V | Q4_K_M | 76.0 GB | 27.8 tok/s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 100B | Q4_K_M | 73.0 GB | 27.8 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 86/100 (quality, fit, speed and memory use) sets the ranking. | Leanstral 119B-A6B | Q4_K_M | 81.8 GB | 47.6 tok/s | Runs great |
| 87Excellent quality (A+) · 87 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. | Raon-1 mini Preview (30B-A4B) | Q6_K | 32.5 GB | 48.9 tok/s | Runs great |
| 74Great quality (A) · 74 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-4.5 Air (106B-A12B) | Q4_K_M | 77.7 GB | 27.8 tok/s | Runs well |
| 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Sarvam 105B | Q4_K_M | 73.8 GB | 32.8 tok/s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Cascade 2 30B-A3B | Q8_0 | 42.3 GB | 44.5 tok/s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | North Mini Code 1.0 (30B-A3B) | Q8_0 | 41.4 GB | 50.5 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Groot 65B A6B 261023 | Q4_K_M | 81.2 GB | 50.9 tok/s | Runs great |
| 78Great quality (A) · 78 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. | Qwen3 30B-A3B Thinking 2507 | Q8_0 | 42.0 GB | 46.7 tok/s | Runs great |
| 78Great quality (A) · 78 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. | Qwen3 Coder 30B-A3B | Q8_0 | 42.0 GB | 46.7 tok/s | Runs great |
| 77Great quality (A) · 77 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. | Nemotron 3 Nano 30B-A3B | Q8_0 | 42.3 GB | 44.5 tok/s | Runs great |
| 77Great quality (A) · 77 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. | Qwen3 30B-A3B Instruct 2507 | Q8_0 | 42.0 GB | 46.7 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 flash Sante | Q4_K_M | 86.6 GB | 58.1 tok/s | Runs great |
| 76Great quality (A) · 76 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. | Qwen3-VL 30B-A3B Thinking | Q8_0 | 42.5 GB | 46.7 tok/s | Runs great |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.7 (230B-A10B) | Q2_K | 102 GB | 50.9 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.7 Flash (198B-A11B) | Q2_K | 89.8 GB | 46.9 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 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. | DiffusionGemma 26B-A4B IT | Q8_0 | 36.6 GB | 39.8 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.5 (230B-A10B) | Q2_K | 102 GB | 50.9 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.5 Flash (196B-A11B) | Q2_K | 89.0 GB | 46.9 tok/s | Runs welltight fit |
| 74Great quality (A) · 74 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-VL 30B-A3B Instruct | Q8_0 | 42.5 GB | 46.7 tok/s | Runs great |
| 74Great quality (A) · 74 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 30B-A3B | Q8_0 | 41.9 GB | 46.7 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.1 (230B-A10B) | Q2_K | 102 GB | 50.9 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | F16 | 49.3 GB | 46.3 tok/s | Runs great |
| 70Great quality (A) · 70 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-Omni 30B-A3B Instruct | Q8_0 | 47.0 GB | 46.7 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2 (230B-A10B) | Q2_K | 102 GB | 50.9 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan A13B (80B-A13B) | Q4_K_M | 58.9 GB | 25.9 tok/s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Lightning 30B-A3B | Q8_0 | 42.3 GB | 50.5 tok/s | Runs great |
| 68Good quality (B) · 68 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. | Llama 4 Scout 17B-16E | Q4_K_M | 76.6 GB | 20.2 tok/s | 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. | Sarvam 30B | Q8_0 | 43.0 GB | 60.2 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 27B | Q5_K_M | 29.1 GB | 11.0 tok/s | 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. | LFM2.5 24B-A2B | Q8_0 | 34.4 GB | 59.3 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | dots.llm1 Instruct | Q3_K_M | 87.1 GB | 30.6 tok/s | Runs welltight fit |
| 90Excellent quality (A+) · 90 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. | Nanbeige4.3 33B | Q4_K_M | 30.7 GB | 11.1 tok/s | Runs well |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 27B | Q5_K_M | 29.1 GB | 11.0 tok/s | Runs well |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Dev 72B | Q6_K | 71.1 GB | 3.5 tok/s | Slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 27B | Q5_K_M | 29.1 GB | 11.0 tok/s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Muse Glimmer 30B | Q5_K_M | 30.0 GB | 10.2 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 79/100 (quality, fit, speed and memory use) sets the ranking. | Command A Reasoning (111B) | Q4_K_M | 77.3 GB | 3.3 tok/s | Slow |
| 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. | ERNIE 4.5 21B-A3B Thinking | Q8_0 | 32.4 GB | 50.5 tok/s | Runs great |
| 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. | Gemma 4 31B | Q4_K_M | 29.5 GB | 11.8 tok/s | Runs well |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | TMax 27B | Q5_K_M | 28.8 GB | 11.1 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 78/100 (quality, fit, speed and memory use) sets the ranking. | Command A (111B) | Q4_K_M | 77.3 GB | 3.3 tok/s | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2.1 (2411) | Q4_K_M | 86.5 GB | 3.0 tok/s | Slow |
| 62Good quality (B) · 62 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. | Axion 1.0 35B | Q8_0 | 46.2 GB | 50.5 tok/s | Runs great |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Command A+ (218B-A25B) | Q2_K | 96.6 GB | 22.5 tok/s | Runs welltight fit |
| 66Good quality (B) · 66 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. | Trinity Mini (26B-A3B) | Q8_0 | 36.6 GB | 50.5 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | K2 Horizon 7B | Q4_K_M | 15.5 GB | 40.9 tok/s | Runs great |
| 73Great quality (A) · 73 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. | Hermes 4 70B | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 73Great quality (A) · 73 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. | Llama 3.3 70B Instruct | Q6_K | 69.4 GB | 3.6 tok/s | Slow |
| 78Great quality (A) · 78 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. | Gemma 4 12B | Q4_K_M | 16.8 GB | 30.8 tok/s | Runs great |
| 73Great quality (A) · 73 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. | InternVL3 78B | Q6_K | 75.8 GB | 3.3 tok/s | 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. | Fara 1.5 27B | Q4_K_M | 26.0 GB | 13.5 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 77/100 (quality, fit, speed and memory use) sets the ranking. | Devstral 2 (123B) | Q3_K_M | 73.0 GB | 3.8 tok/s | Slow |
| 72Great quality (A) · 72 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. | Qwen2.5 72B Instruct | Q6_K | 71.1 GB | 3.5 tok/s | Slow |
| 59Good quality (B) · 59 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. | NorthCUA Mini | Q8_0 | 46.2 GB | 50.5 tok/s | Runs great |
| 72Great quality (A) · 72 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. | Qwen2.5-VL 72B Instruct | Q6_K | 71.7 GB | 3.5 tok/s | Slow |
| 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 70B | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 71Great quality (A) · 71 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. | Tülu 3 70B | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q4_K_M | 14.8 GB | 39.1 tok/s | Runs great |
| 70Great quality (A) · 70 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. | Mellum2.1 Thinking (12B-A2.5B) | Q8_0 | 21.8 GB | 58.3 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q4_K_M | 15.2 GB | 38.1 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 27B | Q4_K_M | 26.0 GB | 13.5 tok/s | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 20.9 GB | 80.0 tok/s | Runs great |
| 64Good quality (B) · 64 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. | ERNIE 4.5 21B-A3B | Q8_0 | 32.5 GB | 50.5 tok/s | Runs great |
| 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q4_K_M | 14.9 GB | 38.2 tok/s | Runs great |
| 69Good quality (B) · 69 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. | Llama 3.1 70B Instruct | Q6_K | 69.4 GB | 3.6 tok/s | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q4_K_M | 14.9 GB | 38.2 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q8_0 | 17.4 GB | 41.7 tok/s | Runs great |
| 71Great quality (A) · 71 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. | Ornith 1.0 9B | Q4_K_M | 14.9 GB | 38.2 tok/s | Runs great |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Medium 3.5 (128B) | Q3_K_M | 74.3 GB | 3.7 tok/s | Slow |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q4_K_M | 14.5 GB | 41.1 tok/s | Runs great |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 70B) | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | QVQ 72B Preview | Q6_K | 71.7 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 74/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.5 33B | Q4_K_M | 30.5 GB | 10.7 tok/s | Runs well |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q8_0 | 17.4 GB | 41.7 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ (08-2024) 104B | Q4_K_M | 74.3 GB | 3.5 tok/s | Slow |
| 76Great quality (A) · 76 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. | Seed-OSS 36B Instruct | Q4_K_M | 33.0 GB | 10.2 tok/s | Runs well |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2 (123B) | Q3_K_M | 72.0 GB | 3.9 tok/s | Slow |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral Large 124B (2411) | Q3_K_M | 72.5 GB | 3.8 tok/s | Slow |
| 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron 70B Instruct | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 68Good quality (B) · 68 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. | Nanbeige4.2 3B | Q8_0 | 14.7 GB | 45.0 tok/s | Runs great |
| 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 70B | Q6_K | 70.5 GB | 3.5 tok/s | Slow |
| 75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4.3 36B | Q4_K_M | 33.0 GB | 10.2 tok/s | Runs well |
| 68Good quality (B) · 68 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. | Nemotron Labs Dory 1.0 4B | Q8_0 | 13.5 GB | 47.1 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 MoE (42B-A6.6B) | Q5_K_M | 39.6 GB | 39.7 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Qwen3-VL 32B Instruct | Q4_K_M | 31.3 GB | 11.0 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 73/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B | Q4_K_M | 30.9 GB | 11.2 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 90B Vision Instruct | Q5_K_M | 75.0 GB | 3.4 tok/s | Slow |
| 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. | UI-Mate 9B | Q4_K_M | 14.8 GB | 39.1 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | UI-Venus 2 9B | Q4_K_M | 14.8 GB | 39.1 tok/s | Runs great |
| 60Good quality (B) · 60 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-VL A3B Thinking 2506 | Q8_0 | 26.4 GB | 50.5 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 72B Instruct | Q6_K | 71.1 GB | 3.5 tok/s | Slow |
| 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 72B Instruct | Q6_K | 71.7 GB | 3.5 tok/s | Slow |
| 56Good quality (B) · 56 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. | LFM2 24B-A2B | Q8_0 | 34.2 GB | 62.2 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ling Mini 2.0 (16B-A1.4B) | F16 | 41.6 GB | 48.6 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q8_0 | 13.5 GB | 45.6 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | F16 | 24.8 GB | 51.5 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 8B | Q4_K_M | 15.5 GB | 41.9 tok/s | Runs great |
| 72Great quality (A) · 72 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 32B | Q4_K_M | 30.9 GB | 11.2 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 72/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 32B | Q4_K_M | 30.9 GB | 11.2 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 72/100 (quality, fit, speed and memory use) sets the ranking. | Skywork OR1 32B | Q4_K_M | 30.9 GB | 11.2 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 72/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 30B | Q4_K_M | 28.8 GB | 12.6 tok/s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2 (24B) | Q4_K_M | 24.8 GB | 15.3 tok/s | Runs well |
| 57Good quality (B) · 57 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. | Groot 19B A3B 261023 | Q8_0 | 29.6 GB | 50.5 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Small (32B-A9B) | Q4_K_M | 28.6 GB | 36.0 tok/s | Runs great |
| 72Great quality (A) · 72 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. | Olmo 3.1 32B Think | Q4_K_M | 29.2 GB | 11.4 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 72/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Plus (14B) | Q4_K_M | 19.4 GB | 25.1 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 71/100 (quality, fit, speed and memory use) sets the ranking. | Apriel 1.5 15B Thinker | Q4_K_M | 19.5 GB | 24.8 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ 104B (04-2024) | Q4_K_M | 74.3 GB | 3.5 tok/s | Slow |
| 70Great quality (A) · 70 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. | EXAONE Deep 32B | Q4_K_M | 30.5 GB | 11.5 tok/s | Runs well |
| 59Good quality (B) · 59 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. | Apertus 70B Instruct | Q6_K | 69.4 GB | 3.6 tok/s | Slow |
| 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. | Phi-4 Reasoning (14B) | Q4_K_M | 19.4 GB | 25.1 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 71/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 32B 0414 | Q4_K_M | 29.2 GB | 11.3 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 71/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 32B (0414) | Q4_K_M | 29.2 GB | 11.3 tok/s | Runs well |
| 62Good quality (B) · 62 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. | Gemma 4 E2B | Q8_0 | 14.3 GB | 81.5 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Vision 15B | Q4_K_M | 19.7 GB | 24.4 tok/s | Runs well |
| 62Good quality (B) · 62 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. | Qwen3.5 4B | Q8_0 | 14.0 GB | 40.2 tok/s | Runs great |
| 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. | DeepSeek R1 Distill Qwen 32B | Q4_K_M | 30.9 GB | 11.2 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 70/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 30B | Q4_K_M | 28.6 GB | 12.8 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 70/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 1.2 (24B) | Q4_K_M | 24.8 GB | 15.3 tok/s | Runs well |
| 61Good quality (B) · 61 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. | TMax 4B | Q8_0 | 13.5 GB | 44.5 tok/s | Runs great |
| 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. | Gemma 3 27B IT | Q4_K_M | 26.3 GB | 13.4 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 70/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Instruct | Q4_K_M | 29.2 GB | 11.4 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 70/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 32B | Q4_K_M | 29.1 GB | 11.5 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 70B Instruct | Q6_K | 69.3 GB | 3.6 tok/s | Slow |
| 60Good quality (B) · 60 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. | Mage-VL-Cowork 4.7B | Q8_0 | 15.0 GB | 39.6 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 72B Instruct | Q6_K | 69.8 GB | 3.5 tok/s | Slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 14B | Q4_K_M | 19.2 GB | 24.9 tok/s | Runs well |
| 60Good quality (B) · 60 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. | Agents-A1 4B | Q8_0 | 13.9 GB | 41.3 tok/s | Runs great |
| 60Good quality (B) · 60 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. | DeepSeek R1 0528 Qwen3 8B | Q5_K_M | 15.8 GB | 37.1 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 8B Instruct | Q4_K_M | 15.3 GB | 42.0 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 8B | Q4_K_M | 15.2 GB | 43.2 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 32B Instruct | Q4_K_M | 30.9 GB | 11.2 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. | Baichuan M2 32B | Q4_K_M | 30.9 GB | 11.2 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. | OpenHands LM 32B | Q4_K_M | 30.9 GB | 11.2 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. | Devstral Small 1.1 (24B) | Q4_K_M | 24.5 GB | 15.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2507 | Q4_K_M | 24.5 GB | 15.6 tok/s | Runs well |
| 60Good quality (B) · 60 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. | MiniCPM5 2B | Q8_0 | 11.8 GB | 74.4 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B Reasoning | Q4_K_M | 18.6 GB | 26.4 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. | MedGemma 27B Text IT | Q4_K_M | 26.1 GB | 13.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | AceReason Nemotron 14B | Q4_K_M | 19.4 GB | 24.9 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 69/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 14B | Q4_K_M | 19.4 GB | 24.9 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 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 14B Instruct | Q4_K_M | 19.4 GB | 24.9 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 69/100 (quality, fit, speed and memory use) sets the ranking. | Apriel Nemotron 15B Thinker | Q4_K_M | 19.6 GB | 24.6 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 69/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 14B | Q4_K_M | 19.1 GB | 24.9 tok/s | Runs well |
| 58Good quality (B) · 58 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. | Fara 1.5 4B | Q8_0 | 13.9 GB | 41.3 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 8B-A1B | F16 | 25.8 GB | 46.0 tok/s | Runs great |
| 52Fair quality (C) · 52 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. | DeepSeek Coder V2 Lite (16B) | Q8_0 | 25.7 GB | 60.2 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 8B | Q4_K_M | 15.5 GB | 41.9 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.5 8B | Q4_K_M | 15.3 GB | 42.3 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 8B | Q4_K_M | 15.0 GB | 45.0 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 32B Instruct | Q4_K_M | 31.3 GB | 11.0 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2506 | Q4_K_M | 24.5 GB | 15.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.2 24B | Q4_K_M | 24.8 GB | 15.3 tok/s | Runs well |
| 46Fair quality (C) · 46 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. | Mixtral 8x22B Instruct | Q3_K_M | 79.6 GB | 11.7 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Nano 9B v2 | Q4_K_M | 14.3 GB | 41.4 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 38B | Q3_K_M | 29.8 GB | 12.4 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B | Q4_K_M | 18.6 GB | 26.4 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Terminal RSI 27B | Q4_K_M | 26.3 GB | 13.3 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 (14B) | Q4_K_M | 19.4 GB | 25.1 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | DeepCoder 14B Preview | Q4_K_M | 19.4 GB | 24.9 tok/s | Runs well |
| 63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 32B Instruct | Q4_K_M | 30.9 GB | 11.2 tok/s | Runs well |
| 56Good quality (B) · 56 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. | Mage-VL 4.7B | Q8_0 | 15.0 GB | 39.6 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 14B | Q4_K_M | 19.6 GB | 24.4 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Instruct | Q8_0 | 26.4 GB | 50.5 tok/s | Runs great |
| 56Good quality (B) · 56 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. | Qwen3 4B Thinking 2507 | Q8_0 | 14.3 GB | 46.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.1V 9B Thinking | Q4_K_M | 15.4 GB | 35.8 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Reka Flash 3.1 (21B) | Q4_K_M | 22.7 GB | 17.6 tok/s | Runs well |
| 63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Hemmingway 1.5 | Q4_K_M | 25.7 GB | 13.7 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 68/100 (quality, fit, speed and memory use) sets the ranking. | MiMo-VL 7B RL | Q4_K_M | 15.1 GB | 44.3 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Reasoning | Q4_K_M | 14.9 GB | 44.6 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B Preview | Q4_K_M | 30.9 GB | 11.2 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2505 | Q4_K_M | 24.5 GB | 15.6 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.1 24B | Q4_K_M | 24.8 GB | 15.3 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 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 57B-A14B Instruct | Q4_K_M | 44.3 GB | 24.2 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 67/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 9B (0414) | Q4_K_M | 14.9 GB | 39.2 tok/s | Runs great |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Mini | Q4_K_M | 40.4 GB | 27.8 tok/s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | F16 | 12.4 GB | 49.9 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mixtral 8x7B DPO | Q4_K_M | 38.4 GB | 26.0 tok/s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova 6.8 Code2Video | Q4_K_M | 26.0 GB | 13.5 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct | Q4_K_M | 19.4 GB | 25.1 tok/s | Runs well |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | MiMo 7B RL | Q5_K_M | 15.6 GB | 38.9 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1R 7B | Q5_K_M | 14.5 GB | 40.1 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 14B | Q4_K_M | 19.4 GB | 24.9 tok/s | Runs well |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 7.8B | Q5_K_M | 15.4 GB | 38.9 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | JanusCoder 14B | Q4_K_M | 19.1 GB | 24.9 tok/s | Runs well |
| 54Fair quality (C) · 54 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. | Qwen3-VL 4B Instruct | Q8_0 | 14.7 GB | 42.2 tok/s | Runs great |
| 54Fair quality (C) · 54 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. | Qwen3 4B Instruct 2507 | Q8_0 | 14.3 GB | 46.6 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 67/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 12B IT | Q4_K_M | 16.9 GB | 30.2 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 8B | Q5_K_M | 14.9 GB | 38.3 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 67/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 8B | Q4_K_M | 15.4 GB | 41.3 tok/s | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 7B Instruct | Q5_K_M | 14.7 GB | 39.9 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 67/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Instruct | Q4_K_M | 14.9 GB | 44.6 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3 24B (2501) | Q4_K_M | 24.5 GB | 15.6 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x7B Instruct | Q4_K_M | 38.4 GB | 26.0 tok/s | Runs well |
| 60Good quality (B) · 60 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. | Falcon-H1 34B Instruct | Q4_K_M | 30.5 GB | 10.9 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Think | Q5_K_M | 15.5 GB | 41.7 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct 1M | Q4_K_M | 19.4 GB | 24.9 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 7B | Q5_K_M | 14.7 GB | 39.9 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 8B v1 | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Codestral 22B | Q4_K_M | 24.2 GB | 16.6 tok/s | Runs well |
| 46Fair quality (C) · 46 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. | Moonlight 16B-A3B Instruct | Q8_0 | 26.0 GB | 50.5 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 110B Chat | Q4_K_M | 79.3 GB | 3.3 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 38B | Q3_K_M | 29.8 GB | 12.4 tok/s | Runs well |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 2 250B | Q2_K | 111 GB | 30.4 tok/s | Runs wellover GPU memory limit |
| 52Fair quality (C) · 52 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. | Granite 4.2 3B | Q8_0 | 13.3 GB | 51.2 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin Mistral 24B Venice Edition | Q4_K_M | 24.8 GB | 15.3 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 66/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Small 24B | Q4_K_M | 24.9 GB | 15.2 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. | Gemma 2 27B IT | Q4_K_M | 27.1 GB | 13.5 tok/s | Runs well |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM4 8B | Q4_K_M | 14.1 GB | 45.0 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Command R (08-2024) 32B | Q4_K_M | 29.8 GB | 11.4 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 7B Instruct | Q5_K_M | 15.2 GB | 40.6 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct | Q5_K_M | 14.7 GB | 39.9 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 8B Reasoning | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 50Fair quality (C) · 50 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. | Qianfan-OCR 4B | Q8_0 | 15.0 GB | 39.6 tok/s | Runs great |
| 50Fair quality (C) · 50 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. | Qwen3 4B | Q8_0 | 14.3 GB | 46.6 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 65/100 (quality, fit, speed and memory use) sets the ranking. | Solar Pro Preview 22B | Q4_K_M | 23.6 GB | 16.6 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 65/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 R1 Mistral 24B | Q4_K_M | 24.5 GB | 15.6 tok/s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.3 Nemotron Super 49B v1.5 | Q2_K | 31.4 GB | 12.1 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-o 2.6 8B | Q4_K_M | 14.6 GB | 42.5 tok/s | Runs great |
| 50Fair quality (C) · 50 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. | Nemotron 3 Nano 4B | Q8_0 | 13.1 GB | 47.2 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 7B Instruct | Q4_K_M | 14.3 GB | 44.4 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B 0414 | Q4_K_M | 14.9 GB | 39.2 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Nano | Q4_K_M | 14.8 GB | 39.1 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. | Aya Vision 32B | Q4_K_M | 30.3 GB | 11.1 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 65/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 32B | Q4_K_M | 29.8 GB | 11.4 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | F16 | 12.7 GB | 45.0 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 32B Instruct | Q4_K_M | 29.5 GB | 11.4 tok/s | Runs well |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Instruct | Q5_K_M | 15.5 GB | 41.7 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct 1M | Q5_K_M | 14.7 GB | 39.9 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 10B Instruct | Q4_K_M | 16.4 GB | 35.7 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 7B Instruct | Q5_K_M | 14.5 GB | 40.1 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Command R 35B (v01) | Q4_K_M | 40.9 GB | 10.5 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 9B IT | Q4_K_M | 16.0 GB | 39.9 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 8B | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 1.1 8B Instruct | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Tiny (7B-A1B) | F16 | 22.7 GB | 62.7 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 22B V2 | Q4_K_M | 24.2 GB | 16.6 tok/s | Runs well |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2.5 8B | Q5_K_M | 15.6 GB | 37.7 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 9B | Q5_K_M | 14.7 GB | 38.3 tok/s | Runs great |
| 48Fair quality (C) · 48 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. | LightOnOCR-3 4B | Q8_0 | 13.9 GB | 41.3 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Thinking 2507 | Q2_K | 104 GB | 21.5 tok/s | Runs wellover GPU memory limit |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | InternLM3 8B Instruct | Q4_K_M | 14.6 GB | 41.8 tok/s | Runs great |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Fara 7B | Q4_K_M | 14.3 GB | 44.4 tok/s | Runs great |
| 46Fair quality (C) · 46 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. | Gemma 3n E4B | Q8_0 | 17.2 GB | 46.9 tok/s | Runs great |
| 47Fair quality (C) · 47 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. | Chandra OCR 2 | Q6_K | 13.4 GB | 48.2 tok/s | Runs great |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Instruct 2507 | Q2_K | 104 GB | 21.5 tok/s | Runs wellover GPU memory limit |
| 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. | Mistral Nemo 12B Instruct | Q4_K_M | 17.6 GB | 30.2 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 8B) | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 8B Instruct | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 235B-A22B Instruct | Q2_K | 105 GB | 21.5 tok/s | Runs wellover GPU memory limit |
| 46Fair quality (C) · 46 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. | Phi-4 Mini Reasoning (3.8B) | Q8_0 | 13.9 GB | 48.8 tok/s | Runs great |
| 40Fair quality (C) · 40 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. | DeepSeek V2 Lite Chat | Q8_0 | 25.7 GB | 60.2 tok/s | Runs great |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat 1M | Q4_K_M | 15.2 GB | 38.8 tok/s | Runs great |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B | Q2_K | 104 GB | 21.5 tok/s | Runs wellover GPU memory limit |
| 45Fair quality (C) · 45 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. | MiniCPM-V 2.6 8B | Q4_K_M | 14.2 GB | 45.5 tok/s | Runs great |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat (2024) | Q4_K_M | 14.9 GB | 39.2 tok/s | Runs great |
| 46Fair quality (C) · 46 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. | Granite 4.1 3B | Q8_0 | 13.1 GB | 55.1 tok/s | Runs great |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | K-EXAONE 236B-A23B | Q2_K | 104 GB | 20.7 tok/s | Runs wellover GPU memory limit |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 7B Instruct | Q5_K_M | 15.0 GB | 40.8 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | F16 | 16.0 GB | 88.3 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 7B | Q5_K_M | 14.7 GB | 39.9 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 7.8B | Q5_K_M | 15.4 GB | 38.9 tok/s | Runs great |
| 45Fair quality (C) · 45 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. | Gemma 3 4B IT | Q8_0 | 13.6 GB | 43.6 tok/s | Runs great |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral 12B (2409) | Q4_K_M | 17.7 GB | 29.7 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 63/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 35B | Q4_K_M | 40.9 GB | 10.5 tok/s | Runs well |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 8B (2410) | Q5_K_M | 15.7 GB | 37.9 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 22B (2409) | Q4_K_M | 24.2 GB | 16.6 tok/s | Runs well |
| 44Fair quality (C) · 44 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. | WeVisOne-VL 4B | Q6_K | 14.0 GB | 52.9 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | DeepHermes 3 Llama 3 8B Preview | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 Llama 3.1 8B | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 8B | Q5_K_M | 15.6 GB | 37.9 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 8B | Q4_K_M | 15.3 GB | 41.4 tok/s | Runs great |
| 44Fair quality (C) · 44 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. | Llama 3.1 Nemotron Nano 4B v1.1 | Q8_0 | 14.6 GB | 41.6 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 8B Instruct | Q4_K_M | 15.1 GB | 45.1 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 8B | Q4_K_M | 15.1 GB | 45.1 tok/s | Runs great |
| 65Good quality (B) · 65 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. | Inkling Small (276B-A12B) | Q2_K | 115 GB | 37.0 tok/s | Slowfar over GPU memory limit |
| 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. | Phi-4 Mini (3.8B) | Q8_0 | 13.9 GB | 48.8 tok/s | Runs great |
| 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. | Ministral 3 3B | Q8_0 | 13.7 GB | 48.7 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 8B-A1B | F16 | 25.6 GB | 46.0 tok/s | Runs great |
| 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. | MedGemma 4B IT | Q8_0 | 13.6 GB | 43.6 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | CodeGeeX4 All 9B | Q4_K_M | 14.9 GB | 39.2 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. | Phi-4 Multimodal Instruct | Q6_K | 14.4 GB | 45.9 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Small 8K Instruct | Q5_K_M | 15.1 GB | 41.2 tok/s | Runs great |
| 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. | North Micro Vision | Q8_0 | 12.4 GB | 75.6 tok/s | Runs great |
| 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. | LFM2.5-VL 3B | Q8_0 | 12.2 GB | 60.1 tok/s | Runs great |
| 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. | Jamba Reasoning 3B | Q8_0 | 12.2 GB | 58.6 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 7B Instruct | Q5_K_M | 14.7 GB | 39.9 tok/s | Runs great |
| 58Good quality (B) · 58 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. | Baichuan M3 235B-A22B | Q2_K | 104 GB | 21.5 tok/s | Runs wellover GPU memory limit |
| 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. | LFM2.5 2.6B | Q8_0 | 11.8 GB | 69.4 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 8B Instruct | Q4_K_M | 15.1 GB | 45.1 tok/s | Runs great |
| 42Fair quality (C) · 42 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. | Hunyuan 4B Instruct | Q8_0 | 14.5 GB | 44.4 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2 8B | Q4_K_M | 14.8 GB | 45.6 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9.4 Llama 3.1 8B | Q4_K_M | 14.8 GB | 45.9 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Llama 3 8B | Q4_K_M | 14.8 GB | 45.9 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.6 8B | Q4_K_M | 14.8 GB | 45.9 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 7B | Q4_K_M | 15.8 GB | 34.3 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 8B | Q4_K_M | 14.4 GB | 42.7 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 7B Instruct | Q4_K_M | 14.3 GB | 44.4 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B | Q4_K_M | 14.1 GB | 45.9 tok/s | Runs great |
| 60Good quality (B) · 60 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. | InternVL3.5 241B-A28B | Q2_K | 107 GB | 17.2 tok/s | Runs wellover GPU memory limit |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM3 3B | Q8_0 | 12.7 GB | 60.9 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 61/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 20B Chat | Q4_K_M | 22.5 GB | 18.5 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Mini Instruct | Q8_0 | 16.1 GB | 49.1 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Jamba2 3B | Q8_0 | 12.0 GB | 61.9 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | F16 | 16.0 GB | 88.3 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | F16 | 11.5 GB | 66.5 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Prover V2 7B | Q5_K_M | 17.7 GB | 44.0 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Mistral-NeMo-Minitron 8B Instruct | Q4_K_M | 15.3 GB | 43.8 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | F16 | 10.9 GB | 90.0 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 8B Instruct | Q4_K_M | 14.8 GB | 45.9 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | AFM 4.5B | Q8_0 | 14.3 GB | 40.6 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium 128K Instruct | Q4_K_M | 19.0 GB | 26.4 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B Arabic | Q4_K_M | 14.1 GB | 45.9 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 61/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 34B Chat | Q4_K_M | 30.8 GB | 10.7 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 61/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 70B Instruct | Q4_K_M | 52.2 GB | 5.3 tok/s | Slow |
| 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. | Granite 4.0 Micro (3B) | Q8_0 | 13.1 GB | 55.1 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium (14B) | Q4_K_M | 18.1 GB | 26.4 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | F16 | 12.7 GB | 46.0 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | TeleOCR | F16 | 12.6 GB | 60.8 tok/s | Runs great |
| 38Basic quality (D) · 38 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. | Phi-3.5 Vision Instruct | Q8_0 | 16.4 GB | 45.2 tok/s | Runs great |
| 38Basic quality (D) · 38 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. | InternLM2.5 7B Chat | Q5_K_M | 15.4 GB | 39.3 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 13B Instruct | Q4_K_M | 20.5 GB | 26.8 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | F16 | 12.0 GB | 55.7 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E2B | F16 | 19.8 GB | 43.2 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 11B Vision Instruct | Q4_K_M | 16.6 GB | 34.5 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. | Qwen3.5 2B | Q8_0 | 11.3 GB | 82.6 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 9B Chat | Q4_K_M | 15.0 GB | 41.7 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 8B Instruct | Q4_K_M | 14.8 GB | 45.7 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 8B | Q4_K_M | 14.8 GB | 45.9 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 8B Instruct | Q4_K_M | 14.4 GB | 45.1 tok/s | Runs great |
| 38Basic quality (D) · 38 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. | MiniCPM3 4B | Q8_0 | 13.4 GB | 46.1 tok/s | Runs great |
| 36Basic quality (D) · 36 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. | Mistral 7B Instruct v0.3 | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 36Basic quality (D) · 36 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. | Zamba2 7B Instruct | Q5_K_M | 14.8 GB | 41.3 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Micro | Q8_0 | 12.2 GB | 58.8 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 128K Instruct | Q8_0 | 16.1 GB | 49.1 tok/s | Runs great |
| 37Basic quality (D) · 37 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | S5 nano | Q8_0 | 14.0 GB | 40.2 tok/s | Runs great |
| 36Basic quality (D) · 36 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. | Falcon3 Mamba 7B Instruct | Q5_K_M | 14.0 GB | 41.8 tok/s | Runs great |
| 36Basic quality (D) · 36 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. | EXAONE 3.0 7.8B Instruct | Q5_K_M | 14.9 GB | 38.9 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 SOLAR 10.7B | Q4_K_M | 16.1 GB | 34.3 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | SOLAR 10.7B Instruct | Q4_K_M | 16.1 GB | 34.3 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 9B V2 | Q4_K_M | 15.0 GB | 41.7 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9 Llama 3 8B | Q4_K_M | 14.8 GB | 45.9 tok/s | Runs great |
| 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. | DeepSeek Coder V2 (236B) | Q2_K | 104 GB | 22.5 tok/s | Runs wellover GPU memory limit |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Mini 3B | Q8_0 | 14.8 GB | 40.1 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 4K Instruct | Q8_0 | 14.5 GB | 49.1 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 2B Instruct | F16 | 14.0 GB | 40.6 tok/s | Runs great |
| 34Basic quality (D) · 34 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. | OLMo 2 7B Instruct | Q5_K_M | 16.1 GB | 41.7 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek LLM 67B Chat | Q4_K_M | 51.5 GB | 5.5 tok/s | Slow |
| 34Basic quality (D) · 34 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. | Hermes 2 Pro Mistral 7B | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 34Basic quality (D) · 34 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. | Starling LM 7B Beta | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Vision 128K Instruct | Q8_0 | 16.4 GB | 45.2 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 3B Instruct | Q8_0 | 12.4 GB | 59.5 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 3B Instruct | Q8_0 | 12.4 GB | 60.7 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 7B Instruct | Q5_K_M | 14.4 GB | 39.9 tok/s | Runs great |
| 50Fair quality (C) · 50 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. | DeepSeek Coder V2 Instruct (0614) | Q2_K | 104 GB | 22.5 tok/s | Runs wellover GPU memory limit |
| 50Fair quality (C) · 50 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. | DeepSeek V2.5 1210 | Q2_K | 104 GB | 22.5 tok/s | Runs wellover GPU memory limit |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Codestral Mamba 7B | Q5_K_M | 14.0 GB | 41.7 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 6.7B Instruct | Q5_K_M | 17.9 GB | 45.1 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 32B Chat | Q4_K_M | 30.8 GB | 11.3 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 33B Instruct | Q4_K_M | 31.2 GB | 11.0 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | F16 | 11.2 GB | 80.0 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 3B Instruct | Q8_0 | 13.1 GB | 58.4 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 58/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 9B Chat | Q4_K_M | 14.6 GB | 41.7 tok/s | Runs great |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (0106) | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | CodeGemma 7B | Q4_K_M | 17.8 GB | 43.1 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 34B | Q4_K_M | 31.0 GB | 10.6 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 | Q2_K | 104 GB | 22.5 tok/s | Runs wellover GPU memory limit |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 3B Instruct | Q8_0 | 13.1 GB | 50.0 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Chat 20B | Q4_K_M | 22.5 GB | 18.5 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Mathstral 7B | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.2 | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mistral 7B DPO | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (1210) | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 3B Instruct | Q8_0 | 12.4 GB | 60.7 tok/s | Runs great |
| 31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 6.7B V2 | Q5_K_M | 17.9 GB | 45.1 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 2.6B | Q8_0 | 11.7 GB | 72.9 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 8B | Q4_K_M | 14.8 GB | 45.9 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 57/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B Instruct | Q4_K_M | 19.2 GB | 23.1 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek MoE 16B Chat | Q8_0 | 27.1 GB | 53.4 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 57/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 70B Chat | Q4_K_M | 52.2 GB | 5.3 tok/s | Slow |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | RecurrentGemma 9B IT | Q4_K_M | 14.8 GB | 38.2 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 20B | Q4_K_M | 22.5 GB | 18.5 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 Llama 3.2 3B | Q8_0 | 13.1 GB | 58.4 tok/s | Runs great |
| 31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | OpenHermes 2.5 Mistral 7B | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Starling LM 7B Alpha | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 7B | Q5_K_M | 15.4 GB | 39.3 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | CogVLM2 Llama 3 Chat 19B | Q4_K_M | 25.0 GB | 18.9 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 57/100 (quality, fit, speed and memory use) sets the ranking. | SQLCoder 7B v2 | Q5_K_M | 17.9 GB | 45.1 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 14B Chat | Q4_K_M | 24.1 GB | 26.0 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 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 8B Instruct (128K) | Q4_K_M | 14.9 GB | 45.7 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | F16 | 11.2 GB | 73.8 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | OLMoE 1B-7B Instruct | F16 | 23.2 GB | 51.5 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Yi 34B Chat | Q4_K_M | 30.8 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 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 34B Instruct | Q4_K_M | 29.7 GB | 10.9 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 1.7B | F16 | 13.8 GB | 42.6 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 MoE A2.7B Chat | Q8_0 | 25.6 GB | 54.9 tok/s | Runs great |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.1 | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 29Basic quality (D) · 29 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. | Qwen2.5-Omni 3B | Q6_K | 13.6 GB | 46.1 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 3B Instruct | Q8_0 | 13.0 GB | 58.0 tok/s | Runs great |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon Mamba 7B Instruct | Q5_K_M | 14.0 GB | 41.8 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 2B Instruct | Q8_0 | 12.1 GB | 74.1 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 2B | Q8_0 | 12.1 GB | 74.1 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 2.4B | Q8_0 | 12.0 GB | 77.8 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 1.2B | F16 | 11.9 GB | 67.5 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 34B Instruct | Q4_K_M | 31.0 GB | 10.9 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 55/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 1.1 7B IT | Q4_K_M | 17.8 GB | 43.1 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. | DeepSeek V2 Chat | Q2_K | 104 GB | 22.5 tok/s | Runs wellover GPU memory limit |
| 27Basic quality (D) · 27 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. | LLaVA 1.6 Mistral 7B | Q5_K_M | 15.2 GB | 40.2 tok/s | Runs great |
| 27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 6B Chat | Q6_K | 14.0 GB | 42.2 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 55/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 13B Instruct | Q3_K_M | 21.9 GB | 36.6 tok/s | Runs great |
| 27Basic quality (D) · 27 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. | Neural Chat 7B v3.3 | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 7B Chat | Q5_K_M | 18.6 GB | 39.4 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 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 20B Instruct | Q4_K_M | 21.3 GB | 18.3 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 2B Instruct | Q8_0 | 12.1 GB | 74.1 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 2B | Q8_0 | 12.1 GB | 71.8 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 1B | F16 | 11.8 GB | 59.2 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 55/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 7B IT | Q4_K_M | 17.8 GB | 43.1 tok/s | Runs great |
| 23Basic quality (D) · 23 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. | Falcon 180B Chat | Q2_K | 80.9 GB | 3.4 tok/s | Slow |
| 27Basic quality (D) · 27 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | WeVisOne VL 2B | Q8_0 | 12.3 GB | 76.8 tok/s | Runs great |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | WizardMath 7B v1.1 | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Zephyr 7B Beta | Q5_K_M | 15.0 GB | 42.0 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite Vision 3.2 2B | Q8_0 | 12.6 GB | 62.9 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | DeepScaleR 1.5B Preview | F16 | 12.6 GB | 48.5 tok/s | Runs great |
| 23Basic quality (D) · 23 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. | Code Llama 7B Instruct | Q5_K_M | 17.9 GB | 45.1 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 1.5B Instruct | F16 | 12.1 GB | 56.1 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 1.5B Instruct | F16 | 12.1 GB | 55.7 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 54/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B (base) | Q4_K_M | 19.2 GB | 23.1 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 2B Instruct | Q8_0 | 11.9 GB | 71.3 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 1.2B | F16 | 11.2 GB | 73.8 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 13B | Q3_K_M | 18.5 GB | 36.6 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | F16 | 10.6 GB | 99.3 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 12B Chat | Q3_K_M | 15.6 GB | 39.2 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 7B | Q5_K_M | 14.4 GB | 42.4 tok/s | Runs great |
| 24Basic quality (D) · 24 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. | SmolVLM2 2.2B Instruct | Q8_0 | 12.8 GB | 83.3 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 1.5B Instruct | F16 | 12.1 GB | 56.1 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 1.6B | F16 | 12.1 GB | 54.7 tok/s | Runs great |
| 24Basic quality (D) · 24 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. | Qwen2-VL 2B Instruct | Q8_0 | 11.4 GB | 84.8 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 53/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 13B Chat | Q3_K_M | 18.5 GB | 36.6 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 53/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 7B | Q5_K_M | 15.7 GB | 45.1 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | Nemotron Mini 4B Instruct | Q8_0 | 13.8 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 52/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 13B Chat | Q3_K_M | 19.0 GB | 34.3 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 1.8B Instruct | F16 | 12.9 GB | 48.3 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 2.2B Instruct | Q8_0 | 12.8 GB | 83.3 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 1.5B | F16 | 12.6 GB | 48.5 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 2.7B Instruct | Q8_0 | 12.0 GB | 70.5 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 3B-A800M Instruct | F16 | 15.9 GB | 73.3 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 1B Instruct | F16 | 11.5 GB | 69.7 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 3B Instruct (128K) | Q8_0 | 15.2 GB | 53.9 tok/s | Runs great |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 7B Chat | Q5_K_M | 16.3 GB | 40.5 tok/s | Runs great |
| 21Basic quality (D) · 21 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | d1 2B | F16 | 12.7 GB | 45.0 tok/s | Runs great |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 7B Chat | Q5_K_M | 15.7 GB | 45.1 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Stable Code Instruct 3B | Q8_0 | 14.4 GB | 67.0 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 1.7B Instruct | F16 | 13.8 GB | 50.5 tok/s | Runs great |
| 19Basic quality (D) · 19 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. | Yi 6B Chat | Q6_K | 14.0 GB | 42.2 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 51/100 (quality, fit, speed and memory use) sets the ranking. | WizardLM 13B v1.2 | Q3_K_M | 18.5 GB | 36.6 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 1.5B Instruct | F16 | 12.0 GB | 56.1 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 13B | Q3_K_M | 18.7 GB | 35.7 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 3B-A800M Instruct | F16 | 15.8 GB | 73.3 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 1B | F16 | 10.8 GB | 86.4 tok/s | Runs great |
| 17Basic quality (D) · 17 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. | DeepSeek LLM 7B Chat | Q5_K_M | 15.7 GB | 44.0 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | StarCoder 15B | Q2_K | 15.3 GB | 38.2 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 1.8B Chat | F16 | 13.4 GB | 45.7 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 51/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 13B v1.5 | Q3_K_M | 18.5 GB | 36.6 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. | StarCoder2 3B | Q8_0 | 12.3 GB | 61.9 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 7B | Q5_K_M | 16.0 GB | 43.1 tok/s | Runs great |
| 17Basic quality (D) · 17 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 2B | F16 | 12.7 GB | 46.0 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 700M | F16 | 10.4 GB | 117 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 1.5B Chat | F16 | 13.4 GB | 58.4 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | StableLM Zephyr 3B | Q8_0 | 13.1 GB | 67.0 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 1B Instruct | F16 | 12.7 GB | 51.7 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Phi-2 2.7B | Q8_0 | 12.4 GB | 67.4 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Spark X2.6 1.7B | F16 | 12.3 GB | 50.5 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 1.5B Instruct | F16 | 12.1 GB | 56.1 tok/s | Runs great |
| 13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 7B v1.5 | Q5_K_M | 15.7 GB | 45.1 tok/s | Runs great |
| 60Good quality (B) · 60 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. | Llama 3.1 Nemotron Ultra 253B v1 | Q2_K | 114 GB | 2.0 tok/s | Very slowfar over GPU memory limit |
| 13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 7B Instruct | Q5_K_M | 14.8 GB | 44.2 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 1.7B Instruct | F16 | 12.6 GB | 50.5 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 1B Instruct | F16 | 12.3 GB | 58.4 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | surya ocr 2.5 | F16 | 10.3 GB | 125 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. | CodeGemma 2B | Q8_0 | 11.6 GB | 74.7 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. | Qwen3 0.6B | F16 | 11.2 GB | 115 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 48/100 (quality, fit, speed and memory use) sets the ranking. | InternLM 7B | Q5_K_M | 15.1 GB | 41.6 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. | Falcon-H1 0.5B Instruct | F16 | 10.0 GB | 166 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 | 9.6 GB | 247 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | DeepSeek Coder 1.3B Instruct | F16 | 13.1 GB | 64.0 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | LLM4Decompile 1.3B V2 | F16 | 13.1 GB | 64.0 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | Gemma 2B IT | Q8_0 | 11.6 GB | 74.7 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. | LFM2-VL 450M | F16 | 9.8 GB | 192 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. | LFM2 350M | F16 | 9.6 GB | 247 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 | 9.5 GB | 254 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | StableLM 2 1.6B Chat | F16 | 12.9 GB | 52.7 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | StableLM 2 Zephyr 1.6B | F16 | 12.9 GB | 52.7 tok/s | Runs great |
| 11Basic quality (D) · 11 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. | GLiDE 0.8B | F16 | 10.4 GB | 115 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. | SmolVLM 500M Instruct | F16 | 10.1 GB | 169 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. | Qwen2.5 0.5B Instruct | F16 | 9.9 GB | 176 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 | 9.3 GB | 376 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 0.5B Instruct | F16 | 10.7 GB | 160 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. | Qwen2.5 Coder 0.5B Instruct | F16 | 9.9 GB | 176 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 | 9.8 GB | 240 tok/s | Runs great |
| 5Basic quality (D) · 5 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 7B Instruct | Q5_K_M | 13.9 GB | 42.1 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | TinyLlama 1.1B Chat | F16 | 11.0 GB | 78.5 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. | Qwen2 0.5B Instruct | F16 | 9.9 GB | 176 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. | ERNIE 4.5 0.3B | F16 | 9.7 GB | 240 tok/s | Runs great |
| 11Basic quality (D) · 11 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. | Falcon 40B Instruct | Q2_K | 25.8 GB | 14.5 tok/s | Runs well |
| 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 | 9.5 GB | 332 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 | 9.4 GB | 320 tok/s | Runs great |
| 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 | 9.6 GB | 240 tok/s | Runs great |
| 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 | 9.2 GB | 665 tok/s | Runs great |
| 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 | 9.1 GB | 960 tok/s | Runs great |
| 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 | 9.1 GB | 665 tok/s | Runs great |
| 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 | 1,121 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 | 314 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 | 311 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 | 988 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 | 1,121 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 | 419 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 | 238 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. | MiniMax M3.1 Flash (428B-A23B) | Q2_K | 181 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 | 251 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-5.3 Flash (320B-A18B) | Q2_K | 137 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. | MiMo V2.6 Flash (310B-A15B) | Q2_K | 133 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 | 314 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 | 431 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 | 311 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 | 322 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 | 338 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 | 670 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 | 420 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 | 238 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 | 419 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. | Intern-S2 (397B-A17B) | Q2_K | 170 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 | 311 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. | Nex N2 Pro (397B-A17B) | Q2_K | 168 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 | 649 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. | Naive N0.5 Flash (309B-A15.5B) | Q2_K | 133 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. | Qwen3.5 397B-A17B | Q2_K | 170 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. | MiniMax M3 (427B) | Q2_K | 181 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 | 311 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. | K2-Horizon (375B-A23B) | Q2_K | 163 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. | Hunyuan Hy3 (295B-A21B) | Q2_K | 131 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. | Beam 1.0 (501B-A23B) | Q2_K | 210 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 | 420 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 | 420 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 V4 Flash (284B-A13B) | Q2_K | 131 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. | MiMo V2.5 (310B-A15B) | Q2_K | 133 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. | Ornith 1.5 397B-A17B | Q2_K | 170 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 | 284 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. | GLM-4.7 (355B-A32B) | Q2_K | 155 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 | 390 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 | 233 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 | 283 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 | 420 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 | 284 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 | 419 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 | 278 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 V4 Flash (April 2026) | Q2_K | 126 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 | 283 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 | 283 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 | 420 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. | Qwen3 Coder 480B-A35B | Q2_K | 203 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. | MiMo V2 Flash (309B-A15B) | Q2_K | 133 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 | 411 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 | 279 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 | 420 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 | 234 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. | GLM-4.6 (355B-A32B) | Q2_K | 155 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 | 283 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. | MiniMax-M1 80K | Q2_K | 192 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5 (355B-A32B) | Q2_K | 155 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-M1 40K | Q2_K | 192 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Large Thinking (400B-A13B) | Q2_K | 169 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 300B-A47B | Q2_K | 131 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 405B | Q2_K | 175 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Pro | Q2_K | 168 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-Text-01 | Q2_K | 192 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 405B | Q2_K | 175 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 | 278 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 405B Instruct | Q2_K | 175 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 4 Maverick (17B x 128E) | Q2_K | 171 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Large | Q2_K | 169 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Grok-1 (314B) | Q2_K | 137 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Snowflake Arctic Instruct | Q2_K | 201 GB | — | Won't run |
Image models on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 9.5 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 4.0 s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Ming-Image 0.1 Design | FP16 | 63.9 GB | 36 s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 79 s | Slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 55 s | Slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP16 | 46.7 GB | 26 s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | FP8 | 59.7 GB | 71 s | Slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 13 s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 7.1 s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanImage 3.0 (80B-A13B) | FP8 | 86.9 GB | 2.0 min | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Fast | FP16 | 64.4 GB | 22 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 2.2 min | Slow |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Dev | FP16 | 64.4 GB | 37 s | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | FP16 | 63.8 GB | 3.3 min | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP16 | 22.7 GB | 5.5 s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image | FP16 | 63.8 GB | 3.3 min | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Full | FP16 | 64.4 GB | 1.7 min | Slow |
| 87Excellent quality (A+) · 87 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. | FireRed-Image-Edit 1.1 | FP16 | 61.2 GB | 2.9 min | Very slow |
| 86Excellent quality (A+) · 86 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. | Qwen-Image-Edit 2511 | FP16 | 61.2 GB | 2.9 min | Very slow |
| 93Excellent quality (A+) · 93 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. | Fibo 2.0 Dev | FP16 | 27.7 GB | 50 s | Slow |
| 70Great quality (A) · 70 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.1 [schnell] | FP16 | 36.4 GB | 4.4 s | Runs great |
| 82Great quality (A) · 82 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.1 Krea [dev] | FP16 | 36.4 GB | 26 s | Runs well |
| 78Great quality (A) · 78 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 [klein] 4B | FP16 | 18.1 GB | 2.2 s | Runs great |
| 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. | ERNIE-Image | FP16 | 34.0 GB | 48 s | Slow |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [dev] | FP16 | 36.4 GB | 26 s | Runs well |
| 82Great quality (A) · 82 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. | FLUX.1 Kontext [dev] | FP16 | 37.0 GB | 48 s | Slow |
| 82Great quality (A) · 82 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. | MOSS-Image SFT | FP16 | 29.3 GB | 31 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Fill [dev] | FP16 | 36.4 GB | 28 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | FP16 | 22.7 GB | 37 s | Runs well |
| 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Large Turbo | FP16 | 30.0 GB | 3.5 s | Runs great |
| 70Great quality (A) · 70 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. | CogView4 6B | FP16 | 33.9 GB | 40 s | Runs well |
| 60Good quality (B) · 60 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. | Kolors | FP16 | 19.8 GB | 8.8 s | Runs great |
| 66Good quality (B) · 66 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. | Stable Diffusion 3.5 Large | FP16 | 30.0 GB | 24 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Chroma1-HD | FP8 | 16.4 GB | 40 s | Runs well |
| 62Good quality (B) · 62 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. | Juggernaut XL v9 | FP16 | 8.9 GB | 9.9 s | Runs great |
| 62Good quality (B) · 62 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. | RealVisXL V5.0 | FP16 | 8.9 GB | 9.9 s | Runs great |
| 72Great quality (A) · 72 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. | Iris-3B | FP16 | 17.3 GB | 35 s | Runs well |
| 60Good quality (B) · 60 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. | Animagine XL 4.0 | FP16 | 8.9 GB | 9.3 s | Runs great |
| 60Good quality (B) · 60 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. | Illustrious XL v0.1 | FP16 | 8.9 GB | 9.3 s | Runs great |
| 58Good quality (B) · 58 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. | DreamShaper XL v2 Turbo | FP16 | 8.9 GB | 2.9 s | Runs great |
| 58Good quality (B) · 58 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. | Pony Diffusion V6 XL | FP16 | 8.9 GB | 8.4 s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3 Medium | FP16 | 17.4 GB | 6.8 s | Runs great |
| 56Good quality (B) · 56 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. | Animagine XL 3.1 | FP16 | 8.9 GB | 9.3 s | Runs great |
| 55Good quality (B) · 55 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. | Stable Diffusion XL 1.0 | FP16 | 8.9 GB | 9.9 s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Lumina-Image 2.0 | FP8 | 7.5 GB | 14 s | Runs well |
| 66Good quality (B) · 66 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. | OmniGen2 | FP16 | 18.0 GB | 35 s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Medium | FP8 | 10.4 GB | 12 s | Runs great |
| 54Fair quality (C) · 54 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. | SDXL-Lightning (4-step) | FP16 | 8.9 GB | 1.5 s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | PixArt-Σ XL 1024 | FP16 | 12.8 GB | 3.3 s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Playground v2.5 | FP8 | 5.6 GB | 15 s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Stable Cascade | FP8 | 8.1 GB | 9.9 s | Runs great |
| 58Good quality (B) · 58 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. | AuraFlow v0.3 | FP16 | 18.5 GB | 31 s | Runs well |
| 52Fair quality (C) · 52 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. | Hunyuan-DiT v1.2 | FP16 | 9.3 GB | 13 s | Runs great |
| 48Fair quality (C) · 48 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. | Kandinsky 3 | FP16 | 25.9 GB | 20 s | Runs well |
| 40Fair quality (C) · 40 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. | SDXL Turbo | FP16 | 7.6 GB | 0.3 s | Runs great |
| 42Fair quality (C) · 42 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. | Realistic Vision V5.1 | FP16 | 2.8 GB | 2.6 s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 2.8 GB | 2.6 s | Runs great |
| 35Basic quality (D) · 35 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. | Stable Diffusion 1.5 | FP16 | 2.8 GB | 2.6 s | Runs great |
| 30Basic quality (D) · 30 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. | LCM DreamShaper v7 | FP16 | 2.8 GB | 0.6 s | Runs great |
| 28Basic quality (D) · 28 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. | SD Turbo | FP16 | 3.3 GB | 0.2 s | Runs great |
Video models on the NVIDIA RTX Spark N1X (6144-core GPU) (128 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 93/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 3.3 min | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 14.7 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP8 | 66.8 GB | 34.4 min | Slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 14.7 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 1.8 h | Very slow |
| 68Good quality (B) · 68 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. | LTX-Video 13B 0.9.8 (distilled) | FP16 | 47.9 GB | 2.2 min | Runs great |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 58.8 min | Very slow |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 58.8 min | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 26.4 min | Slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 66.1 min | Very slow |
| 78Great quality (A) · 78 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. | Wan 2.2 Animate 14B | FP16 | 65.2 GB | 69.8 min | Very slow |
| 78Great quality (A) · 78 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. | Wan 2.1 VACE 14B | FP16 | 64.6 GB | 80.8 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Step-Video T2V (30B) | FP16 | 78.2 GB | 1.9 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 T2V 14B 720P | FP16 | 60.8 GB | 88.2 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 720P | FP16 | 59.3 GB | 73.5 min | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP16 | 49.6 GB | 14.7 min | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Wan-Dancer 14B (music to dance) | FP16 | 77.0 GB | 2.7 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 14B | FP16 | 58.0 GB | 73.5 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 S2V 14B (speech to video) | FP16 | 50.4 GB | 36.7 min | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 13B | FP16 | 64.8 GB | 88.2 min | Very slow |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo I2V 13B | FP16 | 64.8 GB | 88.2 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP16 | 41.9 GB | 19.5 min | Slow |
| 74Great quality (A) · 74 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. | Wan 2.1 I2V 14B 480P | FP16 | 46.5 GB | 33.1 min | Slow |
| 74Great quality (A) · 74 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. | SkyReels V2 T2V 14B 540P | FP16 | 49.0 GB | 51.4 min | Very slow |
| 70Great quality (A) · 70 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. | Cosmos-Predict2 14B Video2World | FP16 | 57.6 GB | 58.8 min | Very slow |
| 70Great quality (A) · 70 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. | Wan 2.2 TI2V 5B | FP16 | 43.1 GB | 19.1 min | Slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP8 | 29.8 GB | 39.7 min | Slow |
| 68Good quality (B) · 68 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. | Kandinsky 6.0 Video Lite (3B, video + audio) | FP16 | 31.5 GB | 11.4 min | Runs well |
| 70Great quality (A) · 70 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. | Open-Sora 2.0 (11B) | FP16 | 43.8 GB | 1.8 h | Very slow |
| 60Good quality (B) · 60 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. | Cosmos 1.0 Diffusion 7B Text2World | FP16 | 48.2 GB | 20.2 min | Slow |
| 60Good quality (B) · 60 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. | CogVideoX 1.5 5B | FP16 | 50.3 GB | 33.1 min | Slow |
| 58Good quality (B) · 58 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. | Cosmos-Predict2 2B Video2World | FP16 | 33.6 GB | 9.2 min | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP16 | 17.5 GB | 55 s | Runs great |
| 88Excellent quality (A+) · 88 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. | Cosmos3-Super Image2Video (64B) | FP16 | 53.7 GB | 1.8 h | Very slowCPU offload |
| 45Fair quality (C) · 45 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. | CogVideoX 2B | FP16 | 17.5 GB | 2.2 min | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP8 | 14.9 GB | 6.0 min | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 14.3 GB | 6.0 min | Runs well |
| 55Good quality (B) · 55 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 VACE 1.3B | FP16 | 21.5 GB | 9.6 min | Runs well |
| 55Good quality (B) · 55 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 2.1 T2V 1.3B | FP16 | 19.8 GB | 8.8 min | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Mochi 1 Preview (10B) | FP8 | 26.7 GB | 36.4 min | Slow |
| 52Fair quality (C) · 52 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. | SkyReels V2 Diffusion Forcing 1.3B | FP16 | 23.8 GB | 11.0 min | Runs well |
| 52Fair quality (C) · 52 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. | Allegro (2.8B) | FP16 | 38.2 GB | 44.1 min | Very slow |
| 35Basic quality (D) · 35 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. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 44 s | Runs great |
Decision models on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 13.4 GB | 125 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 10.2 GB | 26 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 13.4 GB | 125 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q8_0 | 13.7 GB | 84 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 10.2 GB | 26 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 13.1 GB | 120 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | F16 | 15.1 GB | 79 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | F16 | 11.9 GB | 60 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 17 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 12 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | LemonDecider 4B | F16 | 10.8 GB | 74 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 10.2 GB | 26 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | zerank-1 small | F16 | 12.5 GB | 66 ms | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 Gemma | F16 | 13.8 GB | 95 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 17.8 GB | 250 ms | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 13 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 9.8 GB | 22 ms | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass ModernBERT Large v3 | F16 | 1.5 GB | 10 ms | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | F16 | 3.8 GB | 4.8 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 407 ms | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 M3 | F16 | 1.9 GB | 22 ms | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeBERTa v3 Large Zero-shot v2.0 | F16 | 1.6 GB | 11 ms | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DuoGuard 0.5B | F16 | 1.7 GB | 19 ms | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 0.6B | F16 | 2.0 GB | 41 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 27B | Q8_0 | 34.8 GB | 354 ms | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | GTE Reranker ModernBERT Base | F16 | 0.9 GB | 8.6 ms | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v2 Base Multilingual | F16 | 1.2 GB | 13 ms | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | ModernBERT Large Zero-shot v2.0 | F16 | 1.5 GB | 10 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | GLiGuard 300M | F16 | 1.1 GB | 10 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Granite Embedding Reranker English R2 | F16 | 0.9 GB | 8.6 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Laya | F16 | 1.5 GB | 10 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | F16 | 0.8 GB | 6.2 ms | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 0.6B | F16 | 10.5 GB | 75 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 8B | Q8_0 | 10.5 GB | 410 ms | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass Base v3 | F16 | 1.0 GB | 6.9 ms | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | ProtectAI DeBERTa v3 Prompt Injection v2 | F16 | 1.0 GB | 9.6 ms | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 4B | Q6_K | 12.7 GB | 216 ms | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | DeBERTa v3 Base Zero-shot v2.0 | F16 | 1.0 GB | 6.8 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2 Base v1 | F16 | 1.1 GB | 7.2 ms | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | HHEM 2.1 Open | F16 | 0.8 GB | 11 ms | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 8B | Q6_K | 15.8 GB | 399 ms | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | LettuceDetect Large | F16 | 1.5 GB | 29 ms | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Safety Guard 8B v3 | Q6_K | 15.6 GB | 391 ms | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Laya Multilingual | F16 | 1.3 GB | 8.9 ms | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 4.1 8B | Q5_K_M | 15.1 GB | 376 ms | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 2B | F16 | 14.2 GB | 99 ms | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER Multi v2.1 | F16 | 1.3 GB | 8.5 ms | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | WildGuard 7B | Q6_K | 15.0 GB | 353 ms | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | BART Large MNLI | F16 | 1.5 GB | 10 ms | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 3.3 8B | Q6_K | 15.8 GB | 398 ms | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | NuExtract 2.0 2B | Q4_K_M | 10.2 GB | 175 ms | Runs well |
| 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | NuExtract 2.0 4B | Q5_K_M | 11.5 GB | 346 ms | Runs well |
| 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 | 4.7 ms | Runs great |
| 64Good quality (B) · 64 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. | ShieldGemma 9B | Q8_0 | 19.3 GB | 281 ms | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 1B | Q8_0 | 10.4 GB | 89 ms | Runs great |
| 66Good quality (B) · 66 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. | ShieldGemma 27B | Q8_0 | 38.4 GB | 821 ms | Slow |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 8B | Q6_K | 15.6 GB | 391 ms | Runs well |
| 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss-safeguard 120B | MXFP4 | 75.4 GB | 2.7 s | Very slow |
| 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 | 44.1 GB | 27.8 s | Very slow |
| 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 4 12B | Q6_K | 19.0 GB | 582 ms | Slow |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Content Safety Reasoning 4B | Q6_K | 12.6 GB | 2.8 s | Very slow |
| 76Great quality (A) · 76 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 20B | MXFP4 | 21.1 GB | 2.1 s | Very slow |
| 79Great quality (A) · 79 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. | DynaGuard 8B | Q8_0 | 17.8 GB | 7.2 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Selene 1 Mini 8B | Q8_0 | 17.6 GB | 6.8 s | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 7B | Q8_0 | 17.0 GB | 6.5 s | Very slow |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | DynaGuard 1.7B | Q6_K | 10.7 GB | 1.3 s | Slow |
| 74Great quality (A) · 74 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. | Prometheus 2 8x7B | Q8_0 | 58.6 GB | 11.5 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. | Prometheus 2 7B | Q8_0 | 16.7 GB | 6.2 s | Very slow |
| 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | GLIDER | Q6_K | 12.7 GB | 2.4 s | Very slow |
| 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Flow Judge v0.1 | Q6_K | 12.7 GB | 2.4 s | Very slow |
Upgrade picks
GPUs that would run more LLMs without offloading, at launch prices. Right now 512 of 619 LLMs run well on your NVIDIA RTX Spark N1X (6144-core GPU) (128 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.