Check my GPU

on

Can the Apple M3 Ultra (512 GB) run MiniMax M2 (230B-A10B)?

88 ptsExcellent (S) · 88 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 173 GB of 384 GB usable, with an estimated speed of 43.3 tok/s.

Best quant
Q4_K_M
Generation speed
43.3 tok/s
Prompt processing
1,761 tok/s
First token (1K prompt)
0.6 s
Largest safe context
192K

Download MiniMax M2 (230B-A10B)

Recommended for the Apple M3 Ultra (512 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Ollama

Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M files (opens in a new tab)

huggingface.co/unsloth/MiniMax-M2-GGUF (opens in a new tab)

ollama run hf.co/unsloth/MiniMax-M2-GGUF

Original weights · Hugging Face

Full-precision files from MiniMax, for fine-tuning, vLLM, Transformers.

huggingface.co/MiniMaxAI/MiniMax-M2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from MiniMax. The weights themselves download from Hugging Face.

github.com/MiniMax-AI/MiniMax-M2 (opens in a new tab)

git clone https://github.com/MiniMax-AI/MiniMax-M2

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.38.0 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.10.4 / 15
Total88.4 / 10088 ptsExcellent (S) · 88 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the Apple M3 Ultra (512 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 125 GB 384 GB 71.1 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.5/15 GGUF · folder (opens in a new tab)
Q3_K_M 145 GB 384 GB 56.0 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.7/15 GGUF · folder (opens in a new tab)
Q4_K_M 173 GB 384 GB 43.3 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15 GGUF · folder (opens in a new tab)
Q5_K_M 196 GB 384 GB 35.8 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 11.8/15 GGUF · folder (opens in a new tab)
Q6_K 221 GB 384 GB 30.0 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 13.3/15 GGUF · folder (opens in a new tab)
Q8_0 276 GB 384 GB 22.0 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
F16 491 GB 384 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

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.