Macs
Which AI models run on the M5 Max (48 GB, 40-core GPU)?
The M5 Max (48 GB, 40-core GPU) has 48 GB of memory, about 36 GB of it usable for a model. 88 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026 · Vendor specs
48 GBmemory
~36 GB usable for a model
—bandwidth: not published
88models run at 4-bit or better
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Llama 3.3 Nemotron Super 49B49B | Q4_K_M | 31 GB | no estimate |
| Qwen3.6-35B-A3B35B MoE | Q4_K_M | 24 GB | ~163 tok/s ModelFit est. |
| Gemma 4 31B30.7B | Q8_0 | 33 GB | ~15 tok/s ModelFit est. |
| Qwen3-Coder-30B-A3B30.5B MoE | Q8_0 | 34 GB | ~80 tok/s ModelFit est. |
| Nemotron 3 Nano 30B-A3B30B MoE | Q4_K_M | 19.6 GB | no estimate |
| Qwen3.8-27B27.3B | Q8_0 | 29 GB | ~18 tok/s ModelFit est. |
| Gemma 4 26B-A4B25.2B MoE | Q8_0 | 30 GB | ~75 tok/s ModelFit est. |
| gpt-oss-20b21B MoE | MXFP4 | 15.1 GB | ~109 tok/s ModelFit est. |
| Nemotron Nano 9B v29B | Q4_K_M | 6.6 GB | no estimate |
| Qwen3.5 9B Instruct9B | Q8_0 | 12.0 GB | ~56 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~98 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~102 tok/s ModelFit est. |
| Mixtral 8x7B Instruct46.7B MoE | Q4_K_M | 32 GB | ~39 tok/s ModelFit est. |
| Flint 40B-A2.5B39.8B MoE | NVFP4 | 24 GB | ~175 tok/s ModelFit est. |
| Sage-A1.535.95B | Q4_K_M | 23 GB | ~163 tok/s ModelFit est. |
| Qwen3.5 35B-A3B Instruct35B MoE | Q4_K_M | 21 GB | ~166 tok/s ModelFit est. |
| Ornith 1.0 35B35B | Q4_K_M | 23 GB | ~166 tok/s ModelFit est. |
| Nanbeige4.3 33B33.1B | Q4_K_M | 22 GB | ~24 tok/s ModelFit est. |
| Poolside Laguna XS.233B | Q4_K_M | 25 GB | no estimate |
| Laguna XS 2.133B | Q4_K_M | 22 GB | ~153 tok/s ModelFit est. |
| Qwen3 32B32B | Q4_K_M | 22 GB | ~24 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 32B32B | Q4_K_M | 21 GB | ~24 tok/s ModelFit est. |
| Olmo 3.1 32B Instruct32B | Q4_K_M | 21 GB | ~24 tok/s ModelFit est. |
| Qwen3 30B30B | Q8_0 | 32 GB | ~79 tok/s ModelFit est. |
| NVIDIA Nemotron Cascade 2 30B-A3B30B MoE | Q6_K | 26 GB | no estimate |
| Cohere North Mini Code30B | Q4_K_M | 20 GB | no estimate |
| Nemotron 3.5 Lightning 30B-A3B30B MoE | Q4_K_M | 27 GB | ~103 tok/s ModelFit est. |
| GLM-4.7-Flash 30B-A3B30B MoE | Q4_K_M | 20 GB | ~116 tok/s ModelFit est. |
| Granite Switch 4.1 30B30B | Q4_K_M | 23 GB | ~22 tok/s ModelFit est. |
| Muse Glimmer 30B29.8B | Q4_K_M | 18.3 GB | ~31 tok/s ModelFit est. |
| Granite 4.2 30B29.3B | Q4_K_M | 17.9 GB | ~27 tok/s ModelFit est. |
| AREX-2 27B27.4B | Q4_K_M | 18.6 GB | ~30 tok/s ModelFit est. |
| Gemma 2 27B Instruct27B | Q4_K_M | 23 GB | ~27 tok/s ModelFit est. |
| Gemma 3 27B Instruct27B | Q4_K_M | 23 GB | ~28 tok/s ModelFit est. |
| Qwen3.5 27B Instruct27B | Q8_0 | 29 GB | ~18 tok/s ModelFit est. |
| Qwen3.6 27B27B | Q8_0 | 32 GB | ~18 tok/s ModelFit est. |
| Jebadiah 27B27B | Q8_0 | 31 GB | ~18 tok/s ModelFit est. |
| Mistral Small 3.124B | Q8_0 | 25 GB | ~19 tok/s ModelFit est. |
| LFM2 24B-A2B Instruct24B MoE | Q4_K_M | 15.3 GB | ~178 tok/s ModelFit est. |
| Devstral Small 2 24B24B | Q4_K_M | 16.6 GB | ~32 tok/s ModelFit est. |
| Mistral Small 22B22B | Q4_K_M | 18.4 GB | ~36 tok/s ModelFit est. |
| Qwen2.5 14B Instruct14B | Q4_K_M | 12.3 GB | ~51 tok/s ModelFit est. |
| Phi-3 Medium 14B14B | Q4_K_M | 12.3 GB | no estimate |
| Phi-4 14B14B | Q8_0 | 15.9 GB | ~31 tok/s ModelFit est. |
| Qwen2.5 Coder 14B14B | Q4_K_M | 12.3 GB | ~51 tok/s ModelFit est. |
| Qwen3 14B14B | Q8_0 | 17.3 GB | ~31 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 14B14B | Q8_0 | 16.0 GB | ~31 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~51 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | no estimate |
| Mistral Nemo 12B12B | Q8_0 | 13.4 GB | ~37 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~60 tok/s ModelFit est. |
| Gemma 4 12B12B | Q8_0 | 14.1 GB | ~37 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q8_0 | 11.2 GB | ~50 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~65 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~90 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~87 tok/s ModelFit est. |
| Jebadiah 9B9B | Q8_0 | 11.0 GB | ~55 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~79 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~66 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~86 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~74 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~224 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~56 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~54 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~76 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~58 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~98 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~61 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~90 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~97 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~113 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | no estimate |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~97 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~167 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~126 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~188 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~163 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~166 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~188 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~183 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~190 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~288 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~295 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~326 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~297 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~344 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~478 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~336 tok/s ModelFit est. |
Speeds come from ModelFit's estimates (CC BY 4.0) where it covers the model, otherwise from our bandwidth formula. Method
Too big for this machine
Llama 3.3 70B (44 GB), Llama 3.1 70B Instruct (44 GB), DeepSeek-R1 Distill Llama 70B (44 GB), Kolibri 1 (46 GB), Qwen3-Next 80B-A3B (53 GB), Nemotron 3 Super 120B-A12B (67 GB), gpt-oss-120b (68 GB), Llama 4 Scout (70 GB), Ling-3.0-flash (71 GB), Qwen3.5 122B-A10B Instruct (75 GB), Nemotron 3.5 Super VL 120B-A12B (76 GB), Devstral 2 123B (78 GB) and more.
Questions
What is the best AI model for the M5 Max (48 GB, 40-core GPU)?
Qwen3.6-35B-A3B at Q4_K_M: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 163 tok/s, ModelFit est.).
How much memory can a model use on the M5 Max (48 GB, 40-core GPU)?
About 36 GB of the 48 GB.