Macs
Which AI models run on the M1 Max (32 GB, 24-core GPU)?
The M1 Max (32 GB, 24-core GPU) has 32 GB of memory, about 21 GB of it usable for a model, and 400 GB/s of memory bandwidth. 70 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026 · Vendor specs
32 GBmemory
~21 GB usable for a model
400 GB/sbandwidth, sets the speed
70models run at 4-bit or better
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Qwen3-Coder-30B-A3B30.5B MoE | Q4_K_M | 20 GB | ~69 tok/s ModelFit est. |
| Nemotron 3 Nano 30B-A3B30B MoE | Q4_K_M | 19.6 GB | ~121 tok/s our est. |
| Qwen3.8-27B27.3B | Q4_K_M | 17.9 GB | ~17 tok/s ModelFit est. |
| Gemma 4 26B-A4B25.2B MoE | Q4_K_M | 17.4 GB | ~60 tok/s ModelFit est. |
| gpt-oss-20b21B MoE | MXFP4 | 15.1 GB | ~60 tok/s ModelFit est. |
| Nemotron Nano 9B v29B | FP16 | 19.4 GB | ~12 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q8_0 | 12.0 GB | ~31 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~54 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~57 tok/s ModelFit est. |
| Olmo 3.1 32B Instruct32B | Q4_K_M | 21 GB | ~14 tok/s ModelFit est. |
| Cohere North Mini Code30B | Q4_K_M | 20 GB | no estimate |
| Nemotron 3.5 Lightning 30B-A3B30B MoE | IQ4_XS | 20 GB | ~116 tok/s our est. |
| GLM-4.7-Flash 30B-A3B30B MoE | Q4_K_M | 20 GB | ~64 tok/s ModelFit est. |
| Muse Glimmer 30B29.8B | Q4_K_M | 18.3 GB | ~17 tok/s ModelFit est. |
| Granite 4.2 30B29.3B | Q4_K_M | 17.9 GB | ~15 tok/s ModelFit est. |
| AREX-2 27B27.4B | Q4_K_M | 18.6 GB | ~16 tok/s ModelFit est. |
| Qwen3.5 27B Instruct27B | Q4_K_M | 17.4 GB | ~17 tok/s ModelFit est. |
| Qwen3.6 27B27B | Q4_K_M | 19.4 GB | ~17 tok/s ModelFit est. |
| Jebadiah 27B27B | Q5_K_M | 21 GB | ~15 tok/s ModelFit est. |
| Mistral Small 3.124B | Q4_K_M | 16.4 GB | ~15 tok/s our est. |
| LFM2 24B-A2B Instruct24B MoE | Q4_K_M | 15.3 GB | ~98 tok/s ModelFit est. |
| Devstral Small 2 24B24B | Q4_K_M | 16.6 GB | ~18 tok/s ModelFit est. |
| Mistral Small 22B22B | Q4_K_M | 18.4 GB | ~20 tok/s ModelFit est. |
| Qwen2.5 14B Instruct14B | Q4_K_M | 12.3 GB | ~28 tok/s ModelFit est. |
| Phi-3 Medium 14B14B | Q4_K_M | 12.3 GB | ~20 tok/s our est. |
| Phi-4 14B14B | Q8_0 | 15.9 GB | ~17 tok/s ModelFit est. |
| Qwen2.5 Coder 14B14B | Q4_K_M | 12.3 GB | ~28 tok/s ModelFit est. |
| Qwen3 14B14B | Q8_0 | 17.3 GB | ~17 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 14B14B | Q8_0 | 16.0 GB | ~17 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~28 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~131 tok/s our est. |
| Mistral Nemo 12B12B | Q8_0 | 13.4 GB | ~21 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~33 tok/s ModelFit est. |
| Gemma 4 12B12B | Q8_0 | 14.1 GB | ~20 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q8_0 | 11.2 GB | ~28 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~36 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~49 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~48 tok/s ModelFit est. |
| Jebadiah 9B9B | Q8_0 | 11.0 GB | ~30 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~44 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~36 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~48 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~41 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~123 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~31 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~30 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~42 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~32 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~54 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~34 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~50 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~54 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~62 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~69 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~54 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~92 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~70 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~104 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~90 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~92 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~104 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~101 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~105 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~159 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~163 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~180 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~164 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~190 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~263 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~185 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
Fits only at 3-bit or lower
Too big for this machine
DeepSeek-R1 Distill Qwen 32B (21 GB), Gemma 4 31B (21 GB), Qwen3.5 35B-A3B Instruct (21 GB), Qwen3 32B (22 GB), Laguna XS 2.1 (22 GB), Nanbeige4.3 33B (22 GB), Granite Switch 4.1 30B (23 GB), Gemma 2 27B Instruct (23 GB), Gemma 3 27B Instruct (23 GB), Ornith 1.0 35B (23 GB), Sage-A1.5 (23 GB), Qwen3.6-35B-A3B (24 GB) and more.
Questions
What is the best AI model for the M1 Max (32 GB, 24-core GPU)?
Qwen3-Coder-30B-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 69 tok/s, ModelFit est.).
How much memory can a model use on the M1 Max (32 GB, 24-core GPU)?
About 21 GB of the 32 GB.
How fast is the M1 Max (32 GB, 24-core GPU) for local LLMs?
Decode speed is limited by memory bandwidth: 400 GB/s. A model that reads 10 GB per token runs at under 40 tokens per second.