← CanIRunLocal · All hardware · All models
With 128 GB unified memory (about 96.0 GB usable by the GPU), these are the best open models that fit. The top pick is gpt-oss 120B (MoE, MXFP4) at MXFP4 (~67.3 GB, ~77 tok/s): ollama run gpt-oss:120b.
Best for coding: gpt-oss 120B (MoE, MXFP4) (gpt-oss:120b), Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class) (nemotron-3.5-bolt:74b-a9b), Qwen3.5 122B-A10B (MoE) (qwen3.5:122b).
Runtimes available for this hardware: Ollama, LM Studio, llama.cpp, MLX.
Open the interactive checker for M4 Max (40c GPU) 128GB| # | Model | Quant | Memory needed | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| 1 | gpt-oss 120B (MoE, MXFP4) | MXFP4 | 67.3 GB | fits in fast memory | ~77 tok/s | ollama run gpt-oss:120b |
| 2 | Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class) | Default | 27.7 GB | fits in fast memory | ~72 tok/s | ollama run nemotron-3.5-bolt:74b-a9b |
| 3 | Qwen3.5 122B-A10B (MoE) | Q4_K_M | 83.7 GB | fits in fast memory | ~34 tok/s | ollama run qwen3.5:122b |
| 4 | Llama 4 Scout 109B (MoE) | Q4_K_M | 69.7 GB | fits in fast memory | ~21 tok/s | ollama run llama4:16x17b |
| 5 | Nemotron 3.5 Super 120B-A12B (MoE) | Q4_K_M | 92.7 GB | fits in fast memory | ~24 tok/s | ollama run nemotron-3.5-super:120b-a12b-q4_K_M |
| 6 | Qwen3-Next 80B-A3B (MoE) | Q8_0 | 87.3 GB | fits in fast memory | ~69 tok/s | ollama run qwen3-next:80b-a3b-instruct-q8_0 |
| 7 | Qwen3.5 35B-A3B (MoE) | Q8_0 | 40.9 GB | fits in fast memory | ~67 tok/s | ollama run qwen3.5:35b-a3b-q8_0 |
| 8 | Qwen3.6 35B-A3B (MoE) | Q8_0 | 40.9 GB | fits in fast memory | ~67 tok/s | ollama run qwen3.6:35b-a3b-q8_0 |
| 9 | Qwen3 30B-A3B (MoE) | Q8_0 | 34.4 GB | fits in fast memory | ~61 tok/s | ollama run qwen3:30b-a3b-q8_0 |
| 10 | Qwen3-Coder 30B-A3B (MoE) | Q8_0 | 33.4 GB | fits in fast memory | ~63 tok/s | ollama run qwen3-coder:30b-a3b-q8_0 |
| 11 | Laguna XS 2.1 33B-A3B (MoE) | Q8_0 | 37.4 GB | fits in fast memory | ~68 tok/s | ollama run laguna-xs-2.1:q8_0 |
| 12 | Bonsai 2 27B (ternary) | Q2_0 | 10.6 GB | fits in fast memory | ~53 tok/s | ollama run bonsai-2:27b |
| 13 | Nemotron 3.5 Lightning 30B-A3B (MoE) | Q8_0 | 36.4 GB | fits in fast memory | ~66 tok/s | ollama run nemotron-3.5-lightning:30b-a3b-q8_0 |
| 14 | GLM-4.7-Flash 30B-A3B (MoE) | Q8_0 | 33.4 GB | fits in fast memory | ~71 tok/s | ollama run glm-4.7-flash:q8_0 |
| 15 | Qwen3-VL 30B-A3B (MoE) | Q8_0 | 35.7 GB | fits in fast memory | ~67 tok/s | ollama run qwen3-vl:30b-a3b-instruct-q8_0 |
| 16 | Gemma 4 26B-A4B (MoE) | Q8_0 | 29.6 GB | fits in fast memory | ~53 tok/s | ollama run gemma4:26b-a4b-it-q8_0 |
| 17 | Ornith-1.5 35B-A3B (MoE) | Default | 24.8 GB | fits in fast memory | ~111 tok/s | ollama run ornith-1.5:35b |
| 18 | gpt-oss 20B (MoE, MXFP4) | MXFP4 | 15.1 GB | fits in fast memory | ~91 tok/s | ollama run gpt-oss:20b |
| 19 | LFM2.5 24B-A2B (MoE) | Q8_0 | 26.2 GB | fits in fast memory | ~105 tok/s | ollama run lfm2.5:24b-a2b-q8_0 |
| 20 | Qwen3-VL 32B | Q8_0 | 38.6 GB | fits in fast memory | ~12 tok/s | ollama run qwen3-vl:32b-instruct-q8_0 |
| 21 | Qwen3 32B | Q8_0 | 37.2 GB | fits in fast memory | ~12 tok/s | ollama run qwen3:32b-q8_0 |
| 22 | DeepSeek R1 Distill Qwen 32B | Q8_0 | 37.2 GB | fits in fast memory | ~12 tok/s | ollama run deepseek-r1:32b-qwen-distill-q8_0 |
| 23 | North Mini Code 1.0 30B (MoE) | Q8_0 | 34.1 GB | fits in fast memory | ~14 tok/s | ollama run north-mini-code-1.0:q8_0 |
| 24 | Muse Glimmer 30B | Q8_0 | 33.4 GB | fits in fast memory | ~14 tok/s | ollama run muse-glimmer:30b-q8_0 |
| 25 | Gemma 4 31B | Q8_0 | 36.5 GB | fits in fast memory | ~13 tok/s | ollama run gemma4:31b-it-q8_0 |
| 26 | Granite 4.2 30B | Q8_0 | 33.1 GB | fits in fast memory | ~14 tok/s | ollama run granite4.2:30b-q8_0 |
| 27 | Qwen3.5 27B | Q8_0 | 32.3 GB | fits in fast memory | ~15 tok/s | ollama run qwen3.5:27b-q8_0 |
| 28 | Qwen3.6 27B | Q8_0 | 32.3 GB | fits in fast memory | ~15 tok/s | ollama run qwen3.6:27b-q8_0 |
| 29 | Gemma 3 27B | Q8_0 | 32.3 GB | fits in fast memory | ~15 tok/s | ollama run gemma3:27b-it-q8_0 |
| 30 | Clef 27B (Cloudflare, decision) | Q8_0 | 32.3 GB | fits in fast memory | ~15 tok/s | ollama run clef:27b-q8_0 |
| 31 | Qwen3.8 27B | Q8_0 | 32.3 GB | fits in fast memory | ~15 tok/s | ollama run qwen3.8:27b-q8_0 |
| 32 | Mistral Small 24B | Q8_0 | 26.8 GB | fits in fast memory | ~17 tok/s | ollama run mistral-small:24b-instruct-2501-q8_0 |
| 33 | Devstral Small 2 24B | Q8_0 | 27.8 GB | fits in fast memory | ~17 tok/s | ollama run devstral-small-2:24b-instruct-2512-q8_0 |
| 34 | Llama 3.3 70B | Q8_0 | 79.1 GB | fits in fast memory | ~6 tok/s | ollama run llama3.3:70b-instruct-q8_0 |
| 35 | DeepSeek R1 Distill Llama 70B | Q8_0 | 79.1 GB | fits in fast memory | ~6 tok/s | ollama run deepseek-r1:70b-llama-distill-q8_0 |
| 36 | Qwen3 14B | Q8_0 | 17.3 GB | fits in fast memory | ~27 tok/s | ollama run qwen3:14b-q8_0 |
| 37 | DeepSeek R1 Distill Qwen 14B | Q8_0 | 17.3 GB | fits in fast memory | ~27 tok/s | ollama run deepseek-r1:14b-qwen-distill-q8_0 |
| 38 | Phi-4 14B | Q8_0 | 17.3 GB | fits in fast memory | ~27 tok/s | ollama run phi4:14b-q8_0 |
| 39 | Ministral 3 14B | Q8_0 | 16.6 GB | fits in fast memory | ~29 tok/s | ollama run ministral-3:14b-instruct-2512-q8_0 |
| 40 | Mixtral 8x7B (MoE) | Q8_0 | 51.8 GB | fits in fast memory | ~16 tok/s | ollama run mixtral:8x7b-instruct-v0.1-q8_0 |
| 41 | Mistral Nemo 12B | Q8_0 | 14.2 GB | fits in fast memory | ~34 tok/s | ollama run mistral-nemo:12b-instruct-2407-q8_0 |
| 42 | Gemma 3 12B | Q8_0 | 14.6 GB | fits in fast memory | ~34 tok/s | ollama run gemma3:12b-it-q8_0 |
| 43 | Gemma 4 12B | Q8_0 | 14.6 GB | fits in fast memory | ~34 tok/s | ollama run gemma4:12b-it-q8_0 |
| 44 | Qwen3.5 9B | Q8_0 | 11.4 GB | fits in fast memory | ~44 tok/s | ollama run qwen3.5:9b-q8_0 |
| 45 | Bonsai 2 9B (ternary) | Q2_0 | 4.6 GB | fits in fast memory | ~137 tok/s | ollama run bonsai-2:9b |
| 46 | Llama 3.2 Vision 11B | Q8_0 | 13.5 GB | fits in fast memory | ~36 tok/s | ollama run llama3.2-vision:11b-instruct-q8_0 |
| 47 | Nimble v3 9B (Bespoke Labs, decision) | Q8_0 | 10.6 GB | fits in fast memory | ~46 tok/s | ollama run nimble-v3:9b-q8_0 |
| 48 | Granite 4.2 8B | Q8_0 | 10.3 GB | fits in fast memory | ~47 tok/s | ollama run granite4.2:8b-q8_0 |
| 49 | Ministral 3 8B | Q8_0 | 11.3 GB | fits in fast memory | ~44 tok/s | ollama run ministral-3:8b-instruct-2512-q8_0 |
| 50 | Qwen3-VL 8B | Q8_0 | 11.2 GB | fits in fast memory | ~45 tok/s | ollama run qwen3-vl:8b-instruct-q8_0 |
| 51 | Qwen3 8B | Q8_0 | 9.9 GB | fits in fast memory | ~49 tok/s | ollama run qwen3:8b-q8_0 |
| 52 | DeepSeek R1 0528 Qwen3 8B | Q8_0 | 9.9 GB | fits in fast memory | ~49 tok/s | ollama run deepseek-r1:8b-0528-qwen3-q8_0 |
| 53 | Ornith-1.5 9B | Default | 8 GB | fits in fast memory | ~66 tok/s | ollama run ornith-1.5:9b |
| 54 | DeepSeek R1 Distill Qwen 7B | Q8_0 | 9.1 GB | fits in fast memory | ~54 tok/s | ollama run deepseek-r1:7b-qwen-distill-q8_0 |
| 55 | Qwen 2.5 VL 7B | Q8_0 | 10.8 GB | fits in fast memory | ~46 tok/s | ollama run qwen2.5vl:7b-q8_0 |
| 56 | MiniCPM-V 2.6 8B | Q8_0 | 10.5 GB | fits in fast memory | ~48 tok/s | ollama run minicpm-v:8b-2.6-q8_0 |
| 57 | Gemma 4 E4B (effective 4.5B) | Q8_0 | 10.3 GB | fits in fast memory | ~49 tok/s | ollama run gemma4:e4b-it-q8_0 |
| 58 | Clef-Flash 9B (Cloudflare, decision) | Q8_0 | 12.4 GB | fits in fast memory | ~40 tok/s | ollama run clef-flash:9b-q8_0 |
| 59 | Gemma 3n E4B (on-device) | Q8_0 | 10.5 GB | fits in fast memory | ~46 tok/s | ollama run gemma3n:e4b-it-q8_0 |
| 60 | LFM2.5 8B-A1B (MoE) | Q8_0 | 9.8 GB | fits in fast memory | ~206 tok/s | ollama run lfm2.5:8b-a1b-q8_0 |
| 61 | Gemma 3n E2B (on-device) | Q8_0 | 7.8 GB | fits in fast memory | ~63 tok/s | ollama run gemma3n:e2b-it-q8_0 |
| 62 | Gemma 4 E2B (effective 2.3B) | Q8_0 | 7.2 GB | fits in fast memory | ~73 tok/s | ollama run gemma4:e2b-it-q8_0 |
| 63 | Qwen3.5 4B | Q8_0 | 6.4 GB | fits in fast memory | ~84 tok/s | ollama run qwen3.5:4b-q8_0 |
| 64 | DeepSeek Coder V2 Lite 16B (MoE) | Q8_0 | 18 GB | fits in fast memory | ~84 tok/s | ollama run deepseek-coder-v2:16b-lite-instruct-q8_0 |
| 65 | Qwen3-VL 4B | Q8_0 | 6.3 GB | fits in fast memory | ~86 tok/s | ollama run qwen3-vl:4b-instruct-q8_0 |
| 66 | Gemma 3 4B | Q8_0 | 6.2 GB | fits in fast memory | ~87 tok/s | ollama run gemma3:4b-it-q8_0 |
| 67 | Qwen3 4B | Q8_0 | 5.2 GB | fits in fast memory | ~99 tok/s | ollama run qwen3:4b-q8_0 |
| 68 | tev1 4B (Together AI, decision) | Q8_0 | 5.4 GB | fits in fast memory | ~95 tok/s | ollama run tev1:4b-q8_0 |
| 69 | Qwen 2.5 32B | Q8_0 | 37.2 GB | fits in fast memory | ~12 tok/s | ollama run qwen2.5:32b-instruct-q8_0 |
| 70 | Qwen 2.5 Coder 32B | Q8_0 | 37.2 GB | fits in fast memory | ~12 tok/s | ollama run qwen2.5-coder:32b-instruct-q8_0 |
| 71 | Ministral 3 3B | Q8_0 | 5.6 GB | fits in fast memory | ~97 tok/s | ollama run ministral-3:3b-instruct-2512-q8_0 |
| 72 | Phi-4 Mini 3.8B | Q8_0 | 4.9 GB | fits in fast memory | ~107 tok/s | ollama run phi4-mini:3.8b-q8_0 |
| 73 | Granite 4.2 3B | Q8_0 | 4.7 GB | fits in fast memory | ~112 tok/s | ollama run granite4.2:3b-q8_0 |
| 74 | Bonsai 2 4B (ternary) | Q2_0 | 2.8 GB | fits in fast memory | ~273 tok/s | ollama run bonsai-2:4b |
| 75 | Qwen 2.5 72B | Q8_0 | 81.1 GB | fits in fast memory | ~6 tok/s | ollama run qwen2.5:72b-instruct-q8_0 |
| 76 | Llama 3.2 3B | Q8_0 | 4.2 GB | fits in fast memory | ~128 tok/s | ollama run llama3.2:3b-instruct-q8_0 |
| 77 | Qwen 2.5 14B | Q8_0 | 17.3 GB | fits in fast memory | ~27 tok/s | ollama run qwen2.5:14b-instruct-q8_0 |
| 78 | Qwen 2.5 Coder 14B | Q8_0 | 17.3 GB | fits in fast memory | ~27 tok/s | ollama run qwen2.5-coder:14b-instruct-q8_0 |
| 79 | Qwen3.5 2B | Q8_0 | 3.8 GB | fits in fast memory | ~162 tok/s | ollama run qwen3.5:2b-q8_0 |
| 80 | Qwen3-VL 2B | Q8_0 | 3.8 GB | fits in fast memory | ~162 tok/s | ollama run qwen3-vl:2b-instruct-q8_0 |
| 81 | Llama 3.1 8B | Q8_0 | 9.5 GB | fits in fast memory | ~51 tok/s | ollama run llama3.1:8b-instruct-q8_0 |
| 82 | Qwen 2.5 7B | Q8_0 | 9.1 GB | fits in fast memory | ~54 tok/s | ollama run qwen2.5:7b-instruct-q8_0 |
| 83 | Qwen 2.5 Coder 7B | Q8_0 | 9.1 GB | fits in fast memory | ~54 tok/s | ollama run qwen2.5-coder:7b-instruct-q8_0 |
| 84 | Qwen3 1.7B | Q8_0 | 2.9 GB | fits in fast memory | ~199 tok/s | ollama run qwen3:1.7b-q8_0 |
| 85 | Mistral 7B v0.3 | Q8_0 | 8.7 GB | fits in fast memory | ~57 tok/s | ollama run mistral:7b-instruct-q8_0 |
| 86 | LLaVA 1.6 7B | Q8_0 | 9.1 GB | fits in fast memory | ~56 tok/s | ollama run llava:7b-v1.6-vicuna-q8_0 |
| 87 | Code Llama 7B | Q8_0 | 8.1 GB | fits in fast memory | ~61 tok/s | ollama run codellama:7b-instruct-q8_0 |
| 88 | DeepSeek R1 Distill Qwen 1.5B | Q8_0 | 2.6 GB | fits in fast memory | ~230 tok/s | ollama run deepseek-r1:1.5b-qwen-distill-q8_0 |
| 89 | SmolLM2 1.7B | Q8_0 | 2.5 GB | fits in fast memory | ~243 tok/s | ollama run smollm2:1.7b |
| 90 | Bonsai 2 2B (ternary) | Q2_0 | 2 GB | fits in fast memory | ~480 tok/s | ollama run bonsai-2:2b |
| 91 | GLM-OCR 0.9B | BF16 | 3.7 GB | fits in fast memory | ~162 tok/s | ollama run glm-ocr:latest |
| 92 | MiniCPM-V 4.6 1B | Q8_0 | 2.9 GB | fits in fast memory | ~230 tok/s | ollama run minicpm-v4.6:q8_0 |
| 93 | Llama 3.2 1B | Q8_0 | 2 GB | fits in fast memory | ~336 tok/s | ollama run llama3.2:1b |
| 94 | LFM2.5 1.2B Thinking | Q8_0 | 1.9 GB | fits in fast memory | ~364 tok/s | ollama run lfm2.5-thinking:1.2b-q8_0 |
| 95 | Gemma 3 1B | Q8_0 | 1.8 GB | fits in fast memory | ~397 tok/s | ollama run gemma3:1b-it-q8_0 |
| 96 | Qwen3.5 0.8B | Q8_0 | 2 GB | fits in fast memory | ~437 tok/s | ollama run qwen3.5:0.8b-q8_0 |
| 97 | Qwen3 0.6B | Q8_0 | 1.5 GB | fits in fast memory | ~526 tok/s | ollama run qwen3:0.6b-q8_0 |
| 98 | Qwen 2.5 3B | Q8_0 | 4.1 GB | fits in fast memory | ~132 tok/s | ollama run qwen2.5:3b-instruct-q8_0 |
| 99 | SmolLM2 360M | FP16 | 1.3 GB | fits in fast memory | ~598 tok/s | ollama run smollm2:360m |
| 100 | SmolLM2 135M | FP16 | 0.9 GB | fits in fast memory | ~1618 tok/s | ollama run smollm2:135m |
| 101 | Qwen 2.5 Coder 1.5B | Q8_0 | 2.3 GB | fits in fast memory | ~273 tok/s | ollama run qwen2.5-coder:1.5b-instruct-q8_0 |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-18.
A project by OnDevice Labs · llms.txt