Apple M5 Max (64 GB) spec sheet
What your Apple M5 Max (64 GB) can run
We check your graphics card or Mac against every model in the catalog. Your browser reports the GPU model but not its memory, so confirm the exact version below.
- Unified memory
- 64.0 GB
- Usable for models
- 48.0 GB
- Memory bandwidth
- 614 GB/s
- FP16 compute
- 18.9 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on your Apple M5 Max (64 GB)
| Grade · points | Model | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.6 35B-A3B | Q6_K | 34.1 GB | 75.1 tok/s | Runs well |
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Gemma 4 26B-A4B | Q8_0 | 32.2 GB | 43.5 tok/s | Runs well |
| 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.5 35B-A3B | Q6_K | 34.1 GB | 75.1 tok/s | Runs well |
| 95 ptsExcellent (S) · 95 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.5 35B-A3B | Q6_K | 34.1 GB | 75.1 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Apodex 1.1 Mini (35B-A3B) | Q6_K | 34.1 GB | 75.1 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Ornith 1.0 35B-A3B | Q6_K | 34.1 GB | 75.1 tok/s | Runs well |
| 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | GLM-4.7 Flash (30B-A3B) | Q8_0 | 38.0 GB | 55.1 tok/s | Runs well |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Agents-A1 35B-A3B | Q6_K | 33.4 GB | 75.1 tok/s | Runs well |
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen AgentWorld 35B-A3B | Q6_K | 33.0 GB | 75.1 tok/s | Runs well |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 36.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Laguna XS 2.1 (33B-A3B) | Q6_K | 33.2 GB | 75.1 tok/s | Runs well |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Nemotron Cascade 2 30B-A3B | Q8_0 | 38.0 GB | 47.2 tok/s | Runs well |
| 91 ptsExcellent (S) · 91 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | North Mini Code 1.0 (30B-A3B) | Q8_0 | 37.1 GB | 55.1 tok/s | Runs well |
| 90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | DiffusionGemma 26B-A4B IT | Q8_0 | 32.2 GB | 41.3 tok/s | Runs well |
| 90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 30B-A3B Thinking 2507 | Q8_0 | 37.6 GB | 50.1 tok/s | Runs well |
| 90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 Coder 30B-A3B | Q8_0 | 37.6 GB | 50.1 tok/s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Nemotron 3 Nano 30B-A3B | Q8_0 | 38.0 GB | 47.2 tok/s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 30B-A3B Instruct 2507 | Q8_0 | 37.6 GB | 50.1 tok/s | Runs well |
| 89 ptsExcellent (S) · 89 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3-VL 30B-A3B Thinking | Q8_0 | 38.2 GB | 50.1 tok/s | Runs well |
| 88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 30B-A3B | Q8_0 | 37.6 GB | 50.1 tok/s | Runs well |
| 88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3-VL 30B-A3B Instruct | Q8_0 | 38.2 GB | 50.1 tok/s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 10.5/15 | Qwen3.8 27B | Q4_K_M | 21.9 GB | 23.4 tok/s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Nemotron 3.5 Lightning 30B-A3B | Q8_0 | 38.0 GB | 55.1 tok/s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Kimi Linear 48B-A3B | Q5_K_M | 39.4 GB | 89.4 tok/s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 10.5/15 | Qwen3.6 27B | Q4_K_M | 21.9 GB | 23.4 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 38.9/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 12.1/15 | Gemma 4 31B | Q4_K_M | 25.1 GB | 20.8 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 10.5/15 | Qwen3.5 27B | Q4_K_M | 21.9 GB | 23.4 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 Coder Next (80B-A3B) | Q3_K_M | 43.7 GB | 140 tok/s | Tight fit |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3-Next 80B-A3B Thinking | Q3_K_M | 44.5 GB | 140 tok/s | Tight fit |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Sarvam 30B | Q8_0 | 38.7 GB | 68.8 tok/s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3-Omni 30B-A3B Instruct | Q6_K | 34.2 GB | 68.2 tok/s | Runs well |
| 85 ptsExcellent (S) · 85 of 100 points: Model quality 31.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3 Next 80B-A3B Instruct | Q3_K_M | 44.5 GB | 140 tok/s | Tight fit |
| 85 ptsExcellent (S) · 85 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 10.4/15 | TMax 27B | Q4_K_M | 21.7 GB | 23.7 tok/s | Runs well |
| 84 ptsGreat (A) · 84 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15 | ERNIE 4.5 21B-A3B Thinking | Q8_0 | 28.0 GB | 55.1 tok/s | Runs well |
| 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Trinity Mini (26B-A3B) | Q8_0 | 32.3 GB | 55.1 tok/s | Runs well |
| 84 ptsGreat (A) · 84 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 10.4/15 | Fara 1.5 27B | Q4_K_M | 21.7 GB | 23.7 tok/s | Runs well |
| 83 ptsGreat (A) · 83 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 10.4/15 | UI-Mate 27B | Q4_K_M | 21.7 GB | 23.7 tok/s | Runs well |
| 83 ptsGreat (A) · 83 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.2/15 | Gemma 4 12B | Q6_K | 14.9 GB | 37.7 tok/s | Runs well |
| 83 ptsGreat (A) · 83 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 13.8/15 | Seed-OSS 36B Instruct | Q4_K_M | 28.6 GB | 18.0 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 12.6/15 | EXAONE 4.5 33B | Q4_K_M | 26.1 GB | 18.9 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 15.0/15 | Llama 3.3 Nemotron Super 49B v1.5 | Q4_K_M | 37.5 GB | 13.0 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 33.8/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 13.8/15 | Hermes 4.3 36B | Q4_K_M | 28.6 GB | 18.0 tok/s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15 | ERNIE 4.5 21B-A3B | Q8_0 | 28.2 GB | 55.1 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 13.0/15 | Qwen3-VL 32B Instruct | Q4_K_M | 26.9 GB | 19.5 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | QwQ 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 14.4/15 | InternVL3.5 38B | Q4_K_M | 30.0 GB | 16.9 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | Qwen3 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | OpenReasoning Nemotron 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | Skywork OR1 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 13.5/15, Memory use 15.0/15 | Hunyuan A13B (80B-A13B) | Q3_K_M | 44.9 GB | 32.3 tok/s | Tight fit |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 11.8/15 | Granite 4.2 30B | Q4_K_M | 24.4 GB | 22.2 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | Ornith 1.5 9B | Q6_K | 12.6 GB | 46.7 tok/s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 11.9/15 | Olmo 3.1 32B Think | Q4_K_M | 24.8 GB | 20.1 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | Qwen3.5 9B | Q6_K | 12.6 GB | 46.7 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 12.6/15 | EXAONE Deep 32B | Q4_K_M | 26.1 GB | 20.3 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.8/15 | Devstral Small 2 (24B) | Q4_K_M | 20.4 GB | 27.0 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 | LFM2 24B-A2B | Q8_0 | 29.9 GB | 71.8 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 33.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | Ornith 1.0 9B | Q6_K | 12.6 GB | 46.7 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15 | gpt-oss 20B | MXFP4 | 16.6 GB | 96.5 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 24.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Phi-3.5 MoE (42B-A6.6B) | Q5_K_M | 35.2 GB | 40.6 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 25.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Solar Open 100B | Q2_K | 47.1 GB | 44.4 tok/s | Tight fit |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 11.9/15 | GLM-4 32B 0414 | Q4_K_M | 24.8 GB | 19.9 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 11.9/15 | GLM-Z1 32B (0414) | Q4_K_M | 24.8 GB | 19.9 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | DeepSeek R1 Distill Qwen 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 14.4/15 | InternVL3 38B | Q4_K_M | 30.0 GB | 16.9 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | TMax 9B | Q6_K | 12.0 GB | 50.3 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 11.6/15 | Granite 4.1 30B | Q4_K_M | 24.2 GB | 22.5 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 24.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ring Flash 2.0 (100B-A6B) | Q2_K | 46.1 GB | 87.4 tok/s | Tight fit |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Ling Mini 2.0 (16B-A1.4B) | F16 | 37.3 GB | 54.4 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 11.9/15 | Olmo 3.1 32B Instruct | Q4_K_M | 24.8 GB | 20.1 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 11.9/15 | EXAONE 4.0 32B | Q4_K_M | 24.7 GB | 20.3 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | Qwen2.5 32B Instruct | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | Baichuan M2 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | OpenHands LM 32B | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 31.0/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Llama 3.3 70B Instruct | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | Apriel 1.5 15B Thinker | Q4_K_M | 15.1 GB | 43.7 tok/s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | Phi-4 Reasoning Plus (14B) | Q4_K_M | 15.1 GB | 44.3 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Ling Flash 2.0 (100B-A6B) | Q2_K | 46.1 GB | 87.4 tok/s | Tight fit |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.8/15 | Magistral Small 1.2 (24B) | Q4_K_M | 20.4 GB | 27.0 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 10.6/15 | Gemma 3 27B IT | Q4_K_M | 22.0 GB | 23.7 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 23.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Sarvam 105B | Q2_K | 47.2 GB | 53.3 tok/s | Tight fit |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 | Kimi-VL A3B Thinking 2506 | Q8_0 | 22.1 GB | 55.1 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 13.0/15 | Qwen2.5-VL 32B Instruct | Q4_K_M | 27.0 GB | 19.4 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 11.6/15 | Granite 4.0 H Small (32B-A9B) | Q4_K_M | 24.2 GB | 36.1 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.4/15 | Phi-4 Reasoning Vision 15B | Q4_K_M | 15.3 GB | 42.9 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 30.2/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 | Kimi Dev 72B | Q3_K_M | 42.8 GB | 11.5 tok/s | Tight fit |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | Phi-4 Reasoning (14B) | Q4_K_M | 15.1 GB | 44.3 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | UI-Mate 9B | Q6_K | 12.4 GB | 47.9 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | UI-Venus 2 9B | Q6_K | 12.4 GB | 47.9 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Devstral Small 1.1 (24B) | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Magistral Small 2507 | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 10.4/15 | MedGemma 27B Text IT | Q4_K_M | 21.7 GB | 24.0 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 28.6/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | Qwen2.5 Coder 32B Instruct | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Gemma 4 E4B | Q8_0 | 13.1 GB | 41.3 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15 | Ling 3.0 Tiny (8B-A1.3B) | F16 | 20.4 GB | 58.6 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.8/15 | QwQ 32B Preview | Q4_K_M | 26.6 GB | 19.8 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 30.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Granite 4.2 8B | Q6_K | 13.0 GB | 51.2 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.8/15 | Mistral Small 3.2 24B | Q4_K_M | 20.4 GB | 27.0 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Magistral Small 2506 | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 | Qwen3 14B | Q4_K_M | 14.8 GB | 43.9 tok/s | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.5/15 | Ministral 3 14B Reasoning | Q5_K_M | 15.7 GB | 38.4 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | Apriel Nemotron 15B Thinker | Q4_K_M | 15.2 GB | 43.4 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | AceReason Nemotron 14B | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | OpenReasoning Nemotron 14B | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | Qwen2.5 Coder 14B Instruct | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.8/15 | Mistral Small 3.1 24B | Q4_K_M | 20.4 GB | 27.0 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 12.6/15 | Falcon-H1 34B Instruct | Q4_K_M | 26.2 GB | 19.3 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Devstral Small 2505 | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 | Hermes 4 14B | Q4_K_M | 14.8 GB | 43.9 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 8.8/15 | Reka Flash 3.1 (21B) | Q4_K_M | 18.3 GB | 31.0 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.5/15 | Ministral 3 14B | Q5_K_M | 15.7 GB | 38.4 tok/s | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Hermes 4 70B | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | DeepSeek R1 0528 Qwen3 8B | Q8_0 | 14.3 GB | 40.3 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 7.8/15, Memory use 15.0/15 | InternVL3 78B | Q3_K_M | 45.5 GB | 10.7 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 7.1/15 | InternVL3.5 8B | Q8_0 | 14.7 GB | 38.7 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | InternVL3 14B | Q4_K_M | 15.3 GB | 42.9 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.6/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 | Qwen2.5 72B Instruct | Q3_K_M | 42.7 GB | 11.5 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | Phi-4 (14B) | Q4_K_M | 15.1 GB | 44.2 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.6/45, Memory fit 24.0/25, Speed 8.0/15, Memory use 15.0/15 | Qwen2.5-VL 72B Instruct | Q3_K_M | 43.1 GB | 11.4 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | DeepCoder 14B Preview | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Mistral Small 3 24B (2501) | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | DeepSeek R1 Distill Llama 70B | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Tülu 3 70B | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.3/15 | Command R (08-2024) 32B | Q4_K_M | 25.5 GB | 20.1 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 15.0/15 | Nous Hermes 2 Mixtral 8x7B DPO | Q4_K_M | 34.0 GB | 25.2 tok/s | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 11.0/15 | Gemma 2 27B IT | Q4_K_M | 22.8 GB | 23.9 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Qwen3 8B | Q8_0 | 14.3 GB | 40.3 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 9.6/15 | Codestral 22B | Q4_K_M | 19.9 GB | 29.2 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Qwen3-VL 8B Instruct | Q6_K | 12.8 GB | 51.3 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | DeepSeek R1 Distill Qwen 14B | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 | LFM2.5 8B-A1B | F16 | 21.5 GB | 50.8 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | Qwen2.5 14B Instruct | Q4_K_M | 15.0 GB | 44.2 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 15.0/15 | Jamba 1.5 Mini | Q4_K_M | 36.0 GB | 27.0 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.9/15 | Voxtral Small 24B | Q4_K_M | 20.6 GB | 26.8 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 | DeepSeek Coder V2 Lite (16B) | Q8_0 | 21.3 GB | 68.8 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 9.8/15 | Dolphin Mistral 24B Venice Edition | Q4_K_M | 20.4 GB | 27.0 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 12.5/15 | Aya Vision 32B | Q4_K_M | 26.0 GB | 19.6 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Llama 3.1 70B Instruct | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 | JanusCoder 14B | Q4_K_M | 14.8 GB | 43.9 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.3/15 | Aya Expanse 32B | Q4_K_M | 25.5 GB | 20.1 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.1/15 | OLMo 2 32B Instruct | Q4_K_M | 25.2 GB | 20.1 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 15.0/15 | Command R 35B (v01) | Q4_K_M | 36.5 GB | 18.6 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 15.0/15 | Mixtral 8x7B Instruct | Q4_K_M | 34.0 GB | 25.2 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 | Kimi-VL A3B Instruct | Q8_0 | 22.1 GB | 55.1 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | GLM-4.1V 9B Thinking | Q6_K | 13.2 GB | 43.8 tok/s | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 | MiMo-VL 7B RL | Q8_0 | 14.5 GB | 39.8 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Granite 4.1 8B | Q6_K | 13.0 GB | 51.2 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Seed-Coder 8B Reasoning | Q8_0 | 14.3 GB | 40.0 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 | Qwen2.5 14B Instruct 1M | Q4_K_M | 15.1 GB | 43.9 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Hermes 3 (Llama 3.1 70B) | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | MiniCPM-V 4.5 8B | Q6_K | 12.8 GB | 51.8 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Gemma 3 12B IT | Q5_K_M | 13.8 GB | 43.9 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 15.0/15 | Qwen2 57B-A14B Instruct | Q4_K_M | 39.9 GB | 23.2 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 9.7/15 | Dolphin 3.0 R1 Mistral 24B | Q4_K_M | 20.2 GB | 27.5 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 9.3/15 | Solar Pro Preview 22B | Q4_K_M | 19.3 GB | 29.3 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 8.0/15, Memory use 15.0/15 | QVQ 72B Preview | Q3_K_M | 43.1 GB | 11.4 tok/s | Tight fit |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | Gemma 4 E2B | Q8_0 | 9.9 GB | 64.5 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Qwen3.5 4B | Q8_0 | 9.6 GB | 70.9 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Nemotron Nano 9B v2 | Q6_K | 11.9 GB | 50.7 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 24.9/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Llama 3.1 Nemotron 70B Instruct | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Seed-Coder 8B Instruct | Q8_0 | 14.3 GB | 40.0 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 24.9/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 | Apertus v1.5 70B | Q3_K_M | 42.4 GB | 11.7 tok/s | Tight fit |
| 71 ptsGood (B) · 71 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | MiMo 7B RL | Q8_0 | 13.9 GB | 42.2 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 27.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 | TMax 4B | Q8_0 | 9.2 GB | 78.5 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 25.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | GLM-Z1 9B (0414) | Q6_K | 12.5 GB | 47.9 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | EXAONE Deep 7.8B | Q8_0 | 13.8 GB | 42.3 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | InternVL3 8B | Q8_0 | 13.3 GB | 41.6 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 15.0/15 | Aya 23 35B | Q4_K_M | 36.5 GB | 18.6 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Agents-A1 4B | Q8_0 | 9.5 GB | 72.8 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Falcon-H1R 7B | Q8_0 | 12.9 GB | 43.5 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 24.2/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 | Qwen2 72B Instruct | Q3_K_M | 42.8 GB | 11.5 tok/s | Tight fit |
| 71 ptsGood (B) · 71 of 100 points: Model quality 24.2/45, Memory fit 24.0/25, Speed 8.0/15, Memory use 15.0/15 | Qwen2-VL 72B Instruct | Q3_K_M | 43.1 GB | 11.4 tok/s | Tight fit |
| 71 ptsGood (B) · 71 of 100 points: Model quality 24.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Ministral 3 8B | Q6_K | 12.9 GB | 50.5 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15 | Moonlight 16B-A3B Instruct | Q8_0 | 21.6 GB | 55.1 tok/s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Llama 3.1 Nemotron Nano 8B v1 | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Qwen2.5 Coder 7B Instruct | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Olmo 3 7B Think | Q8_0 | 13.7 GB | 45.3 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | MiniCPM4 8B | Q8_0 | 13.4 GB | 40.3 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Fara 1.5 4B | Q8_0 | 9.5 GB | 72.8 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | OpenReasoning Nemotron 7B | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 9.6/15 | Mistral Small 22B (2409) | Q4_K_M | 19.9 GB | 29.2 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | Mage-VL 4.7B | Q8_0 | 10.7 GB | 69.7 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Falcon 3 10B Instruct | Q6_K | 14.2 GB | 43.7 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | Qwen3 4B Thinking 2507 | Q8_0 | 9.9 GB | 82.2 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Qwen2.5-VL 7B Instruct | Q8_0 | 13.7 GB | 39.9 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 | Hunyuan 7B Instruct | Q8_0 | 13.5 GB | 44.1 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Apertus 70B Instruct | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 69 ptsGood (B) · 69 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Qwen2.5 7B Instruct | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Mistral Nemo 12B Instruct | Q5_K_M | 14.4 GB | 43.9 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 12.7/15 | Yi 1.5 34B Chat | Q4_K_M | 26.4 GB | 18.9 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | Granite 4.2 3B | F16 | 12.4 GB | 41.6 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 | Qwen3-VL 4B Instruct | Q8_0 | 10.4 GB | 74.4 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | InternVL2.5 8B | Q8_0 | 14.1 GB | 40.9 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | DeepSeek R1 Distill Llama 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | GLM-4 9B 0414 | Q6_K | 12.5 GB | 47.9 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 21.9/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Llama 3 70B Instruct | Q3_K_M | 41.7 GB | 11.9 tok/s | Tight fit |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Olmo 3 7B Instruct | Q8_0 | 13.7 GB | 45.3 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | Qwen3 4B Instruct 2507 | Q8_0 | 9.9 GB | 82.2 tok/s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Fara 7B | Q8_0 | 13.7 GB | 39.9 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.9/45, Memory fit 24.0/25, Speed 8.1/15, Memory use 15.0/15 | Qwen2.5-Math 72B Instruct | Q3_K_M | 41.4 GB | 11.5 tok/s | Tight fit |
| 68 ptsGood (B) · 68 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | MiniCPM-o 2.6 8B | Q6_K | 12.0 GB | 51.9 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 | Pixtral 12B (2409) | Q5_K_M | 14.6 GB | 43.2 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Gemma 2 9B IT | Q6_K | 13.6 GB | 48.7 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Qwen2.5 7B Instruct 1M | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Falcon-H1 7B Instruct | Q8_0 | 12.9 GB | 43.5 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 13.6/15, Memory use 8.7/15 | InternLM2.5 20B Chat | Q4_K_M | 18.2 GB | 32.7 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15 | Granite 4.0 H Tiny (7B-A1B) | F16 | 18.4 GB | 76.1 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Hermes 3 (Llama 3.1 8B) | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Llama 3.1 8B Instruct | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 | DeepSeek V2 Lite Chat | Q8_0 | 21.3 GB | 68.8 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 | MiniCPM-V 2.6 8B | Q8_0 | 13.5 GB | 40.8 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | InternLM3 8B Instruct | Q6_K | 12.1 GB | 51.2 tok/s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 20.8/45, Memory fit 24.0/25, Speed 8.2/15, Memory use 15.0/15 | Llama 3.2 90B Vision Instruct | Q2_K | 43.2 GB | 12.0 tok/s | Tight fit |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Granite 3.2 8B Instruct | Q8_0 | 14.4 GB | 40.4 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Granite 3.3 8B | Q8_0 | 14.4 GB | 40.4 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | GLM-4 9B Chat 1M | Q6_K | 12.9 GB | 47.5 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Ministral 8B (2410) | Q8_0 | 14.1 GB | 41.2 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.7/15 | Phi-3 Medium 128K Instruct | Q5_K_M | 16.0 GB | 38.4 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 8.4/15 | OLMo 2 13B Instruct | Q5_K_M | 17.5 GB | 39.1 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | DeepHermes 3 Llama 3 8B Preview | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Dolphin 3.0 Llama 3.1 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Tülu 3 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | GLM-4 9B Chat (2024) | Q6_K | 12.5 GB | 47.9 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | EXAONE 3.5 7.8B | Q8_0 | 13.8 GB | 42.3 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 | LFM2 8B-A1B | F16 | 21.2 GB | 50.8 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | Qwen3 4B | Q8_0 | 9.9 GB | 82.2 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 12.9/15 | DeepSeek Coder 33B Instruct | Q4_K_M | 26.9 GB | 19.5 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.7/15 | Qwen1.5 32B Chat | Q4_K_M | 26.4 GB | 20.0 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | Falcon 3 7B Instruct | Q8_0 | 13.3 GB | 44.3 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Qwen2.5-Omni 7B | Q6_K | 13.7 GB | 42.0 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.3/15 | Phi-3 Medium (14B) | Q5_K_M | 15.2 GB | 38.4 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | DeepSeek R1 Distill Qwen 7B | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Gemma 3n E4B | Q8_0 | 12.9 GB | 42.1 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 12.8/15 | LLaVA 1.6 34B | Q4_K_M | 26.6 GB | 18.7 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | Granite 3.1 8B Instruct | Q8_0 | 14.4 GB | 40.4 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15 | Nemotron 3 Nano 4B | Q8_0 | 8.8 GB | 83.2 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Apertus v1.5 8B | Q6_K | 12.8 GB | 50.6 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | InternVL2 8B | Q8_0 | 14.1 GB | 40.9 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Dolphin 2.9.4 Llama 3.1 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Hermes 2 Pro Llama 3 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | OpenChat 3.6 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | CodeGeeX4 All 9B | Q6_K | 12.5 GB | 47.9 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Granite 4.1 3B | F16 | 11.9 GB | 44.8 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Qwen2-VL 7B Instruct | Q8_0 | 13.7 GB | 39.9 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | Phi-3 Small 8K Instruct | Q8_0 | 13.3 GB | 44.7 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | Command R7B | Q8_0 | 13.3 GB | 41.1 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | Qwen2 7B Instruct | Q8_0 | 13.0 GB | 43.4 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.1/15 | Mistral-NeMo-Minitron 8B Instruct | Q8_0 | 14.7 GB | 39.3 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 26.1/45, Memory fit 10.0/25, Speed 14.6/15, Memory use 15.0/15 | GLM-4.6V | Q2_K | 49.1 GB | 37.8 tok/s | Runs with offload |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 | Llama 3.2 11B Vision Instruct | Q6_K | 14.5 GB | 42.2 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Llama 3 8B Instruct | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 | DeepSeek Prover V2 7B | Q8_0 | 15.8 GB | 47.8 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 25.4/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 | Mistral Small 4 (119B-A6B) | Q2_K | 52.4 GB | 75.5 tok/s | Runs with offload |
| 65 ptsGood (B) · 65 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Aya Vision 8B | Q6_K | 11.9 GB | 52.2 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Phi-4 Mini Reasoning (3.8B) | Q8_0 | 9.6 GB | 86.0 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | Command R7B Arabic | Q8_0 | 13.3 GB | 41.1 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 | Phi-4 Multimodal Instruct | Q8_0 | 11.4 GB | 59.3 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 13.6/15, Memory use 8.7/15 | InternLM2 Chat 20B | Q4_K_M | 18.2 GB | 32.7 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 12.7/15 | Yi 34B Chat | Q4_K_M | 26.4 GB | 18.9 tok/s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 18.8/45, Memory fit 24.0/25, Speed 7.3/15, Memory use 15.0/15 | Code Llama 70B Instruct | Q4_K_M | 47.9 GB | 9.4 tok/s | Tight fit |
| 65 ptsGood (B) · 65 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15 | Jamba Reasoning 3B | F16 | 10.8 GB | 47.6 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15 | LFM2.5-VL 3B | F16 | 10.8 GB | 48.8 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 13.7/15, Memory use 9.9/15 | CogVLM2 Llama 3 Chat 19B | Q4_K_M | 20.6 GB | 33.3 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 14.6/15, Memory use 15.0/15 | GLM-4.5V | Q2_K | 49.1 GB | 37.8 tok/s | Runs with offload |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 | North Micro Vision | F16 | 10.3 GB | 61.4 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Apertus 8B Instruct | Q8_0 | 14.0 GB | 41.0 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Llama 3.1 Nemotron Nano 4B v1.1 | Q8_0 | 10.3 GB | 73.3 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Aya Expanse 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 12.2/15 | Granite Code 34B Instruct | Q4_K_M | 25.4 GB | 19.2 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 | Gemma 3 4B IT | Q8_0 | 9.2 GB | 76.8 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Granite 3.0 8B Instruct | Q8_0 | 13.8 GB | 40.4 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | LFM2.5 2.6B | F16 | 10.0 GB | 56.4 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | InternLM2.5 7B Chat | Q8_0 | 13.7 GB | 42.7 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Nous Hermes 2 SOLAR 10.7B | Q6_K | 14.0 GB | 42.0 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | SOLAR 10.7B Instruct | Q6_K | 14.0 GB | 42.0 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 10.4/15, Memory use 12.8/15 | Code Llama 34B Instruct | Q4_K_M | 26.6 GB | 19.2 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Phi-4 Mini (3.8B) | Q8_0 | 9.6 GB | 86.0 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 13.6/15, Memory use 8.7/15 | InternLM2 Math Plus 20B | Q4_K_M | 18.2 GB | 32.7 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15 | Ministral 3 3B | Q8_0 | 9.4 GB | 85.8 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 | SmolLM3 3B | F16 | 11.2 GB | 49.4 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 | MedGemma 4B IT | Q8_0 | 9.2 GB | 76.8 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 | StarCoder2 15B Instruct | Q4_K_M | 14.8 GB | 40.7 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 24.6/45, Memory fit 10.0/25, Speed 14.6/15, Memory use 15.0/15 | GLM-4.5 Air (106B-A12B) | Q2_K | 50.2 GB | 37.8 tok/s | Runs with offload |
| 64 ptsGood (B) · 64 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15 | Qwen1.5 14B Chat | Q4_K_M | 19.8 GB | 45.8 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | Jamba2 3B | F16 | 10.5 GB | 50.3 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Dolphin 2.9 Llama 3 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | Yi Coder 9B Chat | Q6_K | 12.5 GB | 51.0 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Hunyuan 4B Instruct | Q8_0 | 10.1 GB | 78.3 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Granite 4.0 Micro (3B) | F16 | 11.9 GB | 44.8 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15 | Phi-3.5 Mini Instruct | Q8_0 | 11.7 GB | 86.5 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15 | Unlimited OCR (3B-A0.6B) | F16 | 11.6 GB | 127 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 15.0/15 | DeepSeek LLM 67B Chat | Q3_K_M | 39.1 GB | 12.4 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | EXAONE 3.0 7.8B Instruct | Q8_0 | 13.3 GB | 42.3 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Mistral 7B Instruct v0.3 | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Zamba2 7B Instruct | Q8_0 | 13.0 GB | 44.9 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 23.3/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 | Leanstral 119B-A6B | Q2_K | 52.4 GB | 69.7 tok/s | Runs with offload |
| 63 ptsGood (B) · 63 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | OLMo 2 7B Instruct | Q8_0 | 14.3 GB | 45.3 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 29.0/45, Memory fit 4.0/25, Speed 15.0/15, Memory use 15.0/15 | Qwen3.5 122B-A10B | Q2_K | 54.7 GB | 45.3 tok/s | Heavy offload |
| 62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 | Falcon3 Mamba 7B Instruct | Q8_0 | 12.2 GB | 45.4 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 | DeepSeek Coder 6.7B Instruct | Q8_0 | 15.9 GB | 49.0 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 13.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15 | Code Llama 13B Instruct | Q5_K_M | 20.4 GB | 41.2 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | Phi-3.5 Vision Instruct | Q8_0 | 12.1 GB | 79.6 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | AFM 4.5B | Q8_0 | 9.9 GB | 71.5 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15 | DeepSeek MoE 16B Chat | Q8_0 | 22.7 GB | 59.0 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Hermes 2 Pro Mistral 7B | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Starling LM 7B Beta | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | CodeGemma 7B | Q6_K | 15.2 GB | 52.7 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 | Qwen3.5 2B | F16 | 9.1 GB | 67.1 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15 | Granite 4.0 H Micro | F16 | 10.9 GB | 47.7 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | Qwen2.5-Math 7B Instruct | Q8_0 | 12.8 GB | 43.4 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | OpenChat 3.5 (0106) | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 | Codestral Mamba 7B | Q8_0 | 12.2 GB | 45.3 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | Aya 23 8B | Q8_0 | 14.0 GB | 41.1 tok/s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 13.5/15, Memory use 8.1/15 | Granite Code 20B Instruct | Q4_K_M | 16.9 GB | 32.3 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15 | TMax 2B | F16 | 8.3 GB | 81.0 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 13.6/45, Memory fit 25.0/25, Speed 8.3/15, Memory use 15.0/15 | Llama 2 70B Chat | Q3_K_M | 39.6 GB | 12.2 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | Yi 1.5 9B Chat | Q6_K | 12.1 GB | 51.0 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15 | Phi-3 Mini 128K Instruct | Q8_0 | 11.7 GB | 86.5 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Mathstral 7B | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Mistral 7B Instruct v0.2 | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Nous Hermes 2 Mistral 7B DPO | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | OpenChat 3.5 (1210) | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 | Falcon-H1 3B Instruct | F16 | 11.0 GB | 48.3 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 | Qwen2.5 Coder 3B Instruct | F16 | 10.9 GB | 49.3 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 | MiniCPM3 4B | Q8_0 | 9.0 GB | 81.2 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Llama 3.2 3B Instruct | F16 | 11.8 GB | 47.4 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 27.7/45, Memory fit 4.0/25, Speed 14.6/15, Memory use 15.0/15 | Nemotron 3 Super 120B-A12B | Q2_K | 54.0 GB | 37.8 tok/s | Heavy offload |
| 61 ptsGood (B) · 61 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Granite Code 8B Instruct (128K) | Q8_0 | 14.2 GB | 41.0 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 | Voxtral Mini 3B | Q8_0 | 10.4 GB | 70.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 | Qwen2.5-VL 3B Instruct | F16 | 12.2 GB | 40.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15 | Gemma 3n E2B | Q8_0 | 10.3 GB | 60.7 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 | SQLCoder 7B v2 | Q8_0 | 15.9 GB | 49.0 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | RecurrentGemma 9B IT | Q6_K | 12.4 GB | 46.8 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | Phi-3 Vision 128K Instruct | Q8_0 | 12.1 GB | 79.6 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 27.1/45, Memory fit 4.0/25, Speed 15.0/15, Memory use 15.0/15 | Laguna S 2.1 (118B-A8B) | Q2_K | 53.1 GB | 56.6 tok/s | Heavy offload |
| 61 ptsGood (B) · 61 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Phi-3 Mini 4K Instruct | Q8_0 | 10.1 GB | 86.5 tok/s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 | Qwen1.5 MoE A2.7B Chat | Q8_0 | 21.2 GB | 61.2 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | InternLM2 Math Plus 7B | Q8_0 | 13.7 GB | 42.7 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Qwen3-VL 2B Instruct | F16 | 9.6 GB | 71.5 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 | StarCoder2 15B (base) | Q4_K_M | 14.8 GB | 40.7 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.0/15 | OLMoE 1B-7B Instruct | F16 | 18.8 GB | 58.6 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | OpenHermes 2.5 Mistral 7B | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Starling LM 7B Alpha | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 | Qwen2.5 3B Instruct | F16 | 10.9 GB | 49.3 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 12.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 | Orca 2 13B | Q5_K_M | 17.0 GB | 41.2 tok/s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 | Hermes 3 Llama 3.2 3B | F16 | 11.8 GB | 47.4 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15 | LFM2 2.6B | F16 | 9.7 GB | 59.2 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 22.7/45, Memory fit 10.0/25, Speed 12.2/15, Memory use 15.0/15 | Llama 4 Scout 17B-16E | Q2_K | 49.5 GB | 26.6 tok/s | Runs with offload |
| 59 ptsGood (B) · 59 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Mistral 7B Instruct v0.1 | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15 | Qwen1.5 7B Chat | Q8_0 | 16.9 GB | 42.8 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 25.8/45, Memory fit 4.0/25, Speed 15.0/15, Memory use 15.0/15 | Ling 3.0 Flash (127B-A5B) | Q2_K | 55.8 GB | 88.8 tok/s | Heavy offload |
| 59 ptsGood (B) · 59 of 100 points: Model quality 12.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | Gemma 1.1 7B IT | Q6_K | 15.2 GB | 52.7 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 | Llama 2 13B Chat | Q5_K_M | 17.0 GB | 41.2 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 | Falcon Mamba 7B Instruct | Q8_0 | 12.2 GB | 45.4 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 | LLaVA 1.6 Mistral 7B | Q8_0 | 13.5 GB | 43.6 tok/s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15 | Falcon 3 3B Instruct | F16 | 11.6 GB | 47.1 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Neural Chat 7B v3.3 | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15 | Baichuan 2 13B Chat | Q4_K_M | 16.3 GB | 46.7 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 12.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 | StableLM 2 12B Chat | Q5_K_M | 13.9 GB | 44.2 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 11.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 | Gemma 7B IT | Q6_K | 15.2 GB | 52.7 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | Qwen2.5-Omni 3B | Q8_0 | 10.6 GB | 59.6 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15 | Code Llama 7B Instruct | Q8_0 | 15.9 GB | 49.0 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Granite 3.2 2B Instruct | F16 | 10.2 GB | 60.2 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Granite 3.3 2B | F16 | 10.2 GB | 60.2 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | EXAONE 3.5 2.4B | F16 | 9.9 GB | 63.2 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | WizardMath 7B v1.1 | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15 | Zephyr 7B Beta | Q8_0 | 13.2 GB | 45.6 tok/s | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15 | Qwen3 1.7B | F16 | 9.4 GB | 75.0 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 | StarCoder 15B | Q4_K_M | 14.3 GB | 41.0 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 | Yi 1.5 6B Chat | Q8_0 | 11.1 GB | 54.5 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 9.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.3/15 | LLaVA 1.5 13B | Q5_K_M | 17.3 GB | 40.2 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 9.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 | WizardLM 13B v1.2 | Q5_K_M | 17.0 GB | 41.2 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15 | LFM2.5 1.2B Instruct | F16 | 6.9 GB | 130 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 25.8/45, Memory fit 10.0/25, Speed 6.8/15, Memory use 15.0/15 | Command A Reasoning (111B) | Q2_K | 49.6 GB | 8.2 tok/s | Runs with offload |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Granite 3.1 2B Instruct | F16 | 10.2 GB | 60.2 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Gemma 2 2B | F16 | 10.2 GB | 58.3 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15 | EXAONE 4.0 1.2B | F16 | 7.5 GB | 119 tok/s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 | Granite Vision 3.2 2B | F16 | 11.1 GB | 51.1 tok/s | Runs well |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 6.8/15, Memory use 15.0/15 | Command A (111B) | Q2_K | 49.6 GB | 8.2 tok/s | Runs with offload |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 8.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 | Vicuna 13B v1.5 | Q5_K_M | 17.0 GB | 41.2 tok/s | Runs well |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 | StarCoder2 7B | Q8_0 | 12.6 GB | 46.1 tok/s | Runs well |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 | Granite 3.0 2B Instruct | F16 | 10.0 GB | 57.9 tok/s | Runs well |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Orca 2 7B | Q8_0 | 13.7 GB | 49.0 tok/s | Runs well |
| 56 ptsUsable (C) · 56 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15 | Granite 4.0 H 1B | F16 | 7.4 GB | 104 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 | Baichuan 2 7B Chat | Q8_0 | 14.5 GB | 44.0 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | SmolVLM2 2.2B Instruct | F16 | 10.6 GB | 67.7 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | Granite Code 3B Instruct (128K) | F16 | 14.1 GB | 43.8 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15 | DeepScaleR 1.5B Preview | F16 | 8.2 GB | 85.5 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Llama 2 7B Chat | Q8_0 | 13.7 GB | 49.0 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | Qwen2.5 Coder 1.5B Instruct | F16 | 7.8 GB | 98.9 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | Falcon-H1 1.5B Instruct | F16 | 7.7 GB | 98.2 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 | Qwen2-VL 2B Instruct | F16 | 9.1 GB | 68.9 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 | Stable Code Instruct 3B | F16 | 12.7 GB | 54.4 tok/s | Runs well |
| 55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15 | LFM2 1.2B | F16 | 6.9 GB | 130 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | SmolVLM 2.2B Instruct | F16 | 10.6 GB | 67.7 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 | Zamba2 2.7B Instruct | F16 | 10.1 GB | 57.2 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | DeepSeek LLM 7B Chat | Q8_0 | 13.8 GB | 47.8 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15 | Qwen3.5 0.8B | F16 | 6.3 GB | 175 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15 | Granite 3.1 3B-A800M Instruct | F16 | 11.6 GB | 95.2 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | Qwen2.5 1.5B Instruct | F16 | 7.8 GB | 98.9 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | LFM2-VL 1.6B | F16 | 7.7 GB | 96.4 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15 | Nemotron Mini 4B Instruct | Q8_0 | 9.4 GB | 78.9 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 | Yi 6B Chat | Q8_0 | 11.1 GB | 54.5 tok/s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 22.1/45, Memory fit 10.0/25, Speed 7.0/15, Memory use 15.0/15 | Command R+ (08-2024) 104B | Q2_K | 48.1 GB | 8.7 tok/s | Runs with offload |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 | Hunyuan 1.8B Instruct | F16 | 8.6 GB | 85.1 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15 | LLaVA 1.5 7B | Q8_0 | 14.1 GB | 46.8 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15 | DeepSeek R1 Distill Qwen 1.5B | F16 | 8.2 GB | 85.5 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 | Granite 3.0 3B-A800M Instruct | F16 | 11.4 GB | 95.2 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | SmolLM2 1.7B Instruct | F16 | 9.5 GB | 89.0 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15 | Llama 3.2 1B Instruct | F16 | 7.2 GB | 123 tok/s | Runs well |
| 53 ptsUsable (C) · 53 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15 | StarCoder2 3B | F16 | 10.8 GB | 50.3 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 | Vicuna 7B v1.5 | Q8_0 | 13.7 GB | 49.0 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 | StableLM Zephyr 3B | F16 | 11.4 GB | 54.4 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | Qwen2.5-Math 1.5B Instruct | F16 | 7.6 GB | 98.9 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 27.1/45, Memory fit 4.0/25, Speed 6.4/15, Memory use 15.0/15 | Devstral 2 (123B) | Q2_K | 57.4 GB | 7.2 tok/s | Heavy offload |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | OLMo 7B Instruct | Q8_0 | 12.8 GB | 48.0 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 | InternLM2.5 1.8B Chat | F16 | 9.0 GB | 80.6 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15 | Phi-2 2.7B | F16 | 10.7 GB | 54.8 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 5.0/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 10.3/15 | Falcon 40B Instruct | Q2_K | 21.4 GB | 25.5 tok/s | Runs well |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 20.2/45, Memory fit 10.0/25, Speed 7.0/15, Memory use 15.0/15 | Command R+ 104B (04-2024) | Q2_K | 48.1 GB | 8.7 tok/s | Runs with offload |
| 52 ptsUsable (C) · 52 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15 | Gemma 3 1B | F16 | 6.5 GB | 152 tok/s | Runs well |
| 51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15 | InternLM 7B | Q8_0 | 13.3 GB | 45.1 tok/s | Runs well |
| 51 ptsUsable (C) · 51 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 | Yi Coder 1.5B Chat | F16 | 9.0 GB | 103 tok/s | Runs well |
| 51 ptsUsable (C) · 51 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15 | Falcon 3 1B Instruct | F16 | 8.4 GB | 91.2 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15 | LFM2 700M | F16 | 6.0 GB | 206 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | Qwen2 1.5B Instruct | F16 | 7.8 GB | 98.9 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | CodeGemma 2B | F16 | 9.6 GB | 60.7 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 6.4/15, Memory use 15.0/15 | Mistral Large 2.1 (2411) | Q2_K | 56.4 GB | 7.4 tok/s | Heavy offload |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 25.3/45, Memory fit 4.0/25, Speed 6.3/15, Memory use 15.0/15 | Mistral Medium 3.5 (128B) | Q2_K | 58.5 GB | 7.1 tok/s | Heavy offload |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15 | SmolLM 1.7B Instruct | F16 | 8.3 GB | 89.0 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15 | OLMo 2 1B Instruct | F16 | 7.9 GB | 103 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15 | Gemma 2B IT | F16 | 9.6 GB | 60.7 tok/s | Runs well |
| 50 ptsUsable (C) · 50 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 6.4/15, Memory use 15.0/15 | Mistral Large 2 (123B) | Q2_K | 56.6 GB | 7.4 tok/s | Heavy offload |
| 49 ptsUsable (C) · 49 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 6.4/15, Memory use 15.0/15 | Pixtral Large 124B (2411) | Q2_K | 57.0 GB | 7.3 tok/s | Heavy offload |
| 49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15 | Qwen3 0.6B | F16 | 6.9 GB | 203 tok/s | Runs well |
| 49 ptsUsable (C) · 49 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15 | DeepSeek Coder 1.3B Instruct | F16 | 8.8 GB | 113 tok/s | Runs well |
| 49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 | Falcon-H1 0.5B Instruct | F16 | 5.6 GB | 293 tok/s | Runs well |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15 | LFM2.5 350M | F16 | 5.2 GB | 435 tok/s | Runs well |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 | StableLM 2 1.6B Chat | F16 | 8.5 GB | 92.8 tok/s | Runs well |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 | StableLM 2 Zephyr 1.6B | F16 | 8.5 GB | 92.8 tok/s | Runs well |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 | Falcon 7B Instruct | Q8_0 | 12.1 GB | 45.8 tok/s | Runs well |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 16.4/45, Memory fit 10.0/25, Speed 6.8/15, Memory use 15.0/15 | Qwen1.5 110B Chat | Q2_K | 51.6 GB | 8.1 tok/s | Runs with offload |
| 48 ptsUsable (C) · 48 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.6/15 | LFM2-VL 450M | F16 | 5.4 GB | 338 tok/s | Runs well |
| 47 ptsUsable (C) · 47 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15 | LFM2 350M | F16 | 5.2 GB | 435 tok/s | Runs well |
| 47 ptsUsable (C) · 47 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15 | Granite 4.0 H 350M | F16 | 5.2 GB | 448 tok/s | Runs well |
| 47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15 | SmolVLM 500M Instruct | F16 | 5.8 GB | 299 tok/s | Runs well |
| 47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 | Qwen2.5 0.5B Instruct | F16 | 5.5 GB | 311 tok/s | Runs well |
| 46 ptsUsable (C) · 46 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15 | LFM2.5 230M | F16 | 5.0 GB | 662 tok/s | Runs well |
| 46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15 | Hunyuan 0.5B Instruct | F16 | 6.3 GB | 282 tok/s | Runs well |
| 46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 | Qwen2.5 Coder 0.5B Instruct | F16 | 5.5 GB | 311 tok/s | Runs well |
| 46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.6/15 | SmolLM2 360M Instruct | F16 | 5.5 GB | 423 tok/s | Runs well |
| 45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15 | TinyLlama 1.1B Chat | F16 | 6.7 GB | 138 tok/s | Runs well |
| 45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 | Qwen2 0.5B Instruct | F16 | 5.5 GB | 311 tok/s | Runs well |
| 45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.6/15 | ERNIE 4.5 0.3B | F16 | 5.3 GB | 423 tok/s | Runs well |
| 45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15 | SmolVLM 256M Instruct | F16 | 5.1 GB | 586 tok/s | Runs well |
| 45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15 | Gemma 3 270M | F16 | 5.0 GB | 564 tok/s | Runs well |
| 44 ptsUsable (C) · 44 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15 | SmolLM 360M Instruct | F16 | 5.2 GB | 423 tok/s | Runs well |
| 44 ptsUsable (C) · 44 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15 | SmolLM2 135M Instruct | F16 | 4.9 GB | 1,171 tok/s | Runs well |
| 43 ptsUsable (C) · 43 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15 | Falcon-H1 Tiny 90M Instruct | F16 | 4.7 GB | 1,692 tok/s | Runs well |
| 43 ptsUsable (C) · 43 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15 | SmolLM 135M Instruct | F16 | 4.7 GB | 1,171 tok/s | Runs well |
| 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | gpt-oss 120B | MXFP4 | 71.3 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiMo V2.6 Pro (1T-A42B) | Q2_K | 415 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3.8 Max (2.4T-A95B) | Q2_K | 984 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K3 (2.8T) | Q2_K | 1,117 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-5.3 (753B-A40B) | Q2_K | 307 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiMo V2.6 Flash (310B-A15B) | Q2_K | 129 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V4 Pro (1.6T-A49B) | Q2_K | 665 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3.8 Flash Next (125B-A6B) | Q2_K | 76.6 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-5.2 (753B-A40B) | Q2_K | 307 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Hunyuan Hy4 Preview (780B) | Q2_K | 317 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2.6 (1T) | Q2_K | 416 GB | — | Won't run |
| 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-5.3 Flash (320B-A18B) | Q2_K | 133 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-5.1 (744B-A40B) | Q2_K | 307 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V4 Pro (April 2026) | Q2_K | 644 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3.5 397B-A17B | Q2_K | 166 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax M3 (427B) | Q2_K | 176 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-5 (744B-A40B) | Q2_K | 307 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Hunyuan Hy3 (295B-A21B) | Q2_K | 127 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2.5 (1T) | Q2_K | 416 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2.7 Code (1T) | Q2_K | 416 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V4 Flash (284B-A13B) | Q2_K | 126 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Ornith 1.5 397B-A17B | Q2_K | 166 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3.2 (671B) | Q2_K | 279 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-4.7 (355B-A32B) | Q2_K | 151 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax M2.7 (230B-A10B) | Q2_K | 98.0 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Nemotron 3 Ultra 550B-A55B | Q2_K | 229 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek R1 0528 (671B) | Q2_K | 279 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2 Thinking (1T) | Q2_K | 416 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3.2 Exp | Q2_K | 279 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax M2.5 (230B-A10B) | Q2_K | 98.0 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek R1 (671B) | Q2_K | 273 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V4 Flash (April 2026) | Q2_K | 121 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Step 3.5 Flash (196B-A11B) | Q2_K | 84.6 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3.1 Terminus | Q2_K | 279 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3.1 (671B) | Q2_K | 279 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2 Instruct 0905 (1T) | Q2_K | 416 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax M2.1 (230B-A10B) | Q2_K | 98.0 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3 235B-A22B Thinking 2507 | Q2_K | 100 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3 Coder 480B-A35B | Q2_K | 199 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiMo V2 Flash (309B-A15B) | Q2_K | 129 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Ling 1T | Q2_K | 407 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Mistral Large 3 (675B) | Q2_K | 275 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3 235B-A22B Instruct 2507 | Q2_K | 100 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Solar Open 2 250B | Q2_K | 106 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Kimi K2 Instruct (July 2025) | Q2_K | 416 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax M2 (230B-A10B) | Q2_K | 98.0 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3-VL 235B-A22B Instruct | Q2_K | 100 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | K-EXAONE 236B-A23B | Q2_K | 99.7 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | LongCat Flash Chat (560B) | Q2_K | 229 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Qwen3 235B-A22B | Q2_K | 100 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | InternVL3.5 241B-A28B | Q2_K | 102 GB | — | Won't run |
| 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Llama 3.1 Nemotron Ultra 253B v1 | Q2_K | 110 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Baichuan M3 235B-A22B | Q2_K | 100 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-4.6 (355B-A32B) | Q2_K | 150 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3 0324 (671B) | Q2_K | 279 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax-M1 80K | Q2_K | 187 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | GLM-4.5 (355B-A32B) | Q2_K | 151 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax-M1 40K | Q2_K | 187 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Trinity Large Thinking (400B-A13B) | Q2_K | 165 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | ERNIE 4.5 300B-A47B | Q2_K | 126 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Hermes 4 405B | Q2_K | 171 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | dots.llm1 Instruct | Q2_K | 69.9 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | MiniMax-Text-01 | Q2_K | 187 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Tülu 3 405B | Q2_K | 171 GB | — | Won't run |
| 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V3 (671B) | Q2_K | 273 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek Coder V2 (236B) | Q2_K | 99.3 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek Coder V2 Instruct (0614) | Q2_K | 99.3 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V2.5 1210 | Q2_K | 99.3 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Llama 3.1 405B Instruct | Q2_K | 171 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Llama 4 Maverick (17B x 128E) | Q2_K | 167 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V2.5 | Q2_K | 99.3 GB | — | Won't run |
| 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Jamba 1.5 Large | Q2_K | 164 GB | — | Won't run |
| 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | DeepSeek V2 Chat | Q2_K | 99.3 GB | — | Won't run |
| 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Mixtral 8x22B Instruct | Q2_K | 62.6 GB | — | Won't run |
| 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Grok-1 (314B) | Q2_K | 132 GB | — | Won't run |
| 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Snowflake Arctic Instruct | Q2_K | 196 GB | — | Won't run |
| 3 ptsWon't run (F) · 3 of 100 points: Model quality 3.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 | Falcon 180B Chat | Q2_K | 76.6 GB | — | Won't run |
Image models on your Apple M5 Max (64 GB)
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 15.0/15 | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 10 s | Runs well |
| 86 ptsExcellent (S) · 86 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 10.9/15 | Z-Image Turbo | FP16 | 22.7 GB | 14 s | Runs well |
| 83 ptsGreat (A) · 83 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.7/15 | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 5.7 s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 5.7/15, Memory use 15.0/15 | FLUX.1 Krea [dev] | FP16 | 36.4 GB | 69 s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 | Stable Diffusion 3.5 Large Turbo | FP16 | 30.0 GB | 9.2 s | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 1.9/15, Memory use 15.0/15 | Qwen-Image 2512 | Q8 GGUF | 36.5 GB | 9.9 min | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 5.7/15, Memory use 15.0/15 | FLUX.1 [dev] | FP16 | 36.4 GB | 69 s | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 4.2/15, Memory use 15.0/15 | FLUX.1 Kontext [dev] | FP16 | 37.0 GB | 2.1 min | Runs well |
| 81 ptsGreat (A) · 81 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 15.0/15 | Qwen-Image | FP8 | 35.1 GB | 7.8 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 2.1/15, Memory use 15.0/15 | Qwen-Image-Edit 2511 | Q8 GGUF | 33.9 GB | 8.8 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 5.1/15, Memory use 15.0/15 | HiDream-I1 Dev | FP8 | 33.7 GB | 88 s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 2.8/15, Memory use 15.0/15 | HiDream-I1 Full | Q8 GGUF | 34.9 GB | 5.0 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 15.0/15 | HiDream-I1 Fast | FP8 | 33.7 GB | 52 s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 9.4/15 | FLUX.1 [schnell] | FP8 | 19.6 GB | 10 s | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 5.6/15, Memory use 15.0/15 | FLUX.1 Fill [dev] | FP16 | 36.4 GB | 72 s | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 41.0/45, Memory fit 20.0/25, Speed 3.0/15, Memory use 15.0/15 | FLUX.2 [dev] | Q8 GGUF | 37.9 GB | 4.2 min | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 14.4/15 | Chroma1-HD | FP16 | 30.0 GB | 1.9 min | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 10.9/15 | Z-Image | FP16 | 22.7 GB | 1.6 min | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 4.7/15, Memory use 15.0/15 | CogView4 6B | FP16 | 33.9 GB | 1.7 min | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 6.0/15, Memory use 14.4/15 | Stable Diffusion 3.5 Large | FP16 | 30.0 GB | 63 s | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 9.5/15 | Kolors | FP16 | 19.8 GB | 23 s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 | DreamShaper XL v2 Turbo | FP16 | 8.9 GB | 7.5 s | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 39.7/45, Memory fit 12.0/25, Speed 2.4/15, Memory use 15.0/15 | HunyuanImage 3.0 (80B-A13B) | FP8 | 32.8 GB | 6.7 min | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 | PixArt-Σ XL 1024 | FP16 | 12.8 GB | 8.6 s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.3/15 | SDXL-Lightning (4-step) | FP16 | 8.9 GB | 4.0 s | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 4.9/15, Memory use 8.7/15 | OmniGen2 | FP16 | 18.0 GB | 1.5 min | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 8.9/15 | Stable Diffusion 3.5 Medium | FP16 | 18.4 GB | 34 s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 4.3/15 | Juggernaut XL v9 | FP16 | 8.9 GB | 26 s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 4.3/15 | RealVisXL V5.0 | FP16 | 8.9 GB | 26 s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 6.1/15 | Lumina-Image 2.0 | FP16 | 12.7 GB | 40 s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 4.3/15 | Animagine XL 4.0 | FP16 | 8.9 GB | 24 s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 4.3/15 | Illustrious XL v0.1 | FP16 | 8.9 GB | 24 s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 12.4/15 | Kandinsky 3 | FP16 | 25.9 GB | 52 s | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 5.3/15, Memory use 8.9/15 | AuraFlow v0.3 | FP16 | 18.5 GB | 80 s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 4.7/15 | Stable Diffusion 3 Medium | FP8 | 9.9 GB | 16 s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 2.7/15 | Pony Diffusion V6 XL | FP8 | 5.6 GB | 20 s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 7.2/15, Memory use 4.3/15 | Playground v2.5 | FP16 | 8.9 GB | 43 s | Runs well |
| 62 ptsGood (B) · 62 of 100 points: Model quality 24.7/45, Memory fit 25.0/25, Speed 10.2/15, Memory use 2.7/15 | Animagine XL 3.1 | FP8 | 5.6 GB | 22 s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 2.7/15 | Stable Diffusion XL 1.0 | FP8 | 5.6 GB | 23 s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 | SDXL Turbo | FP16 | 7.6 GB | 0.9 s | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 3.9/15 | Stable Cascade | FP8 | 8.1 GB | 26 s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 8.1/15, Memory use 4.5/15 | Hunyuan-DiT v1.2 | FP16 | 9.3 GB | 34 s | Runs well |
| 60 ptsGood (B) · 60 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 1.3/15 | Realistic Vision V5.1 | FP16 | 2.8 GB | 6.9 s | Runs well |
| 59 ptsGood (B) · 59 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 1.3/15 | DreamShaper 8 | FP16 | 2.8 GB | 6.9 s | Runs well |
| 57 ptsUsable (C) · 57 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 1.3/15 | Stable Diffusion 1.5 | FP16 | 2.8 GB | 6.9 s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 1.3/15 | LCM DreamShaper v7 | FP16 | 2.8 GB | 1.4 s | Runs well |
| 54 ptsUsable (C) · 54 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 1.6/15 | SD Turbo | FP16 | 3.3 GB | 0.5 s | Runs well |
Video models on your Apple M5 Max (64 GB)
| Grade · points | Model | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 80 ptsGreat (A) · 80 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 14.5/15 | LTX-Video 13B 0.9.8 (distilled) | FP8 | 30.1 GB | 5.2 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 37.9/45, Memory fit 23.0/25, Speed 4.4/15, Memory use 15.0/15 | LTX-2.3 | FP8 | 44.3 GB | 34.5 min | Tight fit |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 2.0/15, Memory use 15.0/15 | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 2.9 h | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 38.3/45, Memory fit 25.0/25, Speed 2.0/15, Memory use 15.0/15 | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 2.9 h | Runs well |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 2.1/15, Memory use 15.0/15 | HunyuanVideo 1.5 (8.3B) | FP8 | 38.4 GB | 2.6 h | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 36.2/45, Memory fit 23.0/25, Speed 4.4/15, Memory use 15.0/15 | LTX-2 (19B, video + audio) | FP8 | 44.3 GB | 34.5 min | Tight fit |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 1.8/15, Memory use 15.0/15 | Wan 2.1 I2V 14B 720P | Q8 GGUF | 39.9 GB | 3.7 h | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 1.8/15, Memory use 15.0/15 | Wan 2.1 T2V 14B | Q8 GGUF | 39.3 GB | 3.7 h | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 4.4/15, Memory use 13.5/15 | FramePack I2V (HunyuanVideo 13B) | FP8 | 28.2 GB | 34.5 min | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 2.5/15, Memory use 14.1/15 | Wan 2.2 S2V 14B (speech to video) | Q8 GGUF | 29.3 GB | 1.8 h | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 15.0/15 | Wan 2.2 TI2V 5B | FP8 | 32.4 GB | 44.8 min | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 34.7/45, Memory fit 23.0/25, Speed 1.8/15, Memory use 15.0/15 | Wan 2.2 Animate 14B | Q8 GGUF | 42.7 GB | 3.5 h | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 34.7/45, Memory fit 23.0/25, Speed 1.7/15, Memory use 15.0/15 | Wan 2.1 VACE 14B | Q8 GGUF | 42.8 GB | 4.0 h | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 34.4/45, Memory fit 23.0/25, Speed 1.8/15, Memory use 15.0/15 | SkyReels V2 T2V 14B 720P | FP8 | 41.1 GB | 3.4 h | Tight fit |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 2.4/15, Memory use 14.1/15 | SkyReels V2 T2V 14B 540P | FP8 | 29.3 GB | 2.0 h | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 3.0/15, Memory use 12.6/15 | Wan 2.1 I2V 14B 480P | FP8 | 26.2 GB | 77.5 min | Runs well |
| 73 ptsGreat (A) · 73 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 15.0/15 | Cosmos-Predict2 14B Video2World | FP8 | 38.8 GB | 2.3 h | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 30.1/45, Memory fit 25.0/25, Speed 1.6/15, Memory use 15.0/15 | HunyuanVideo 13B | Q4 GGUF | 38.5 GB | 4.6 h | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 30.1/45, Memory fit 25.0/25, Speed 1.6/15, Memory use 15.0/15 | HunyuanVideo I2V 13B | Q4 GGUF | 38.5 GB | 4.6 h | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 5.3/15, Memory use 15.0/15 | Cosmos-Predict2 2B Video2World | FP16 | 33.6 GB | 23.9 min | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 31.5/45, Memory fit 23.0/25, Speed 1.5/15, Memory use 15.0/15 | Open-Sora 2.0 (11B) | FP16 | 43.8 GB | 4.8 h | Tight fit |
| 70 ptsGood (B) · 70 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15 | LTX-Video 2B | FP16 | 17.5 GB | 2.4 min | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 3.0/15, Memory use 15.0/15 | CogVideoX 1.5 5B | FP8 | 40.0 GB | 77.5 min | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 12.2/15 | CogVideoX 5B I2V | FP16 | 25.3 GB | 17.2 min | Runs well |
| 68 ptsGood (B) · 68 of 100 points: Model quality 33.5/45, Memory fit 18.0/25, Speed 1.6/15, Memory use 15.0/15 | Step-Video T2V (30B) | FP8 | 45.5 GB | 4.7 h | Tight fit |
| 67 ptsGood (B) · 67 of 100 points: Model quality 27.3/45, Memory fit 25.0/25, Speed 2.7/15, Memory use 12.8/15 | Mochi 1 Preview (10B) | FP8 | 26.7 GB | 1.6 h | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 11.6/15 | CogVideoX 5B | FP16 | 24.1 GB | 17.2 min | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 2.4/15, Memory use 15.0/15 | Allegro (2.8B) | FP16 | 38.2 GB | 1.9 h | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 27.0/45, Memory fit 20.0/25, Speed 3.5/15, Memory use 15.0/15 | Cosmos 1.0 Diffusion 7B Text2World | FP16 | 38.7 GB | 55.3 min | Runs well |
| 65 ptsGood (B) · 65 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 5.2/15, Memory use 10.4/15 | Wan 2.1 VACE 1.3B | FP16 | 21.5 GB | 24.9 min | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 5.4/15, Memory use 9.5/15 | Wan 2.1 T2V 1.3B | FP16 | 19.8 GB | 23.0 min | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 11.5/15 | SkyReels V2 Diffusion Forcing 1.3B | FP16 | 23.8 GB | 28.7 min | Runs well |
| 61 ptsGood (B) · 61 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 5.3/15 | CogVideoX 2B | FP8 | 11.0 GB | 5.2 min | Runs well |
| 58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15 | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 1.9 min | Runs well |
Upgrade picks
GPUs that would run more LLMs without offloading, at launch prices. Right now 439 of 536 LLMs run well on your Apple M5 Max (64 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.