Check my GPU

on

Can the Apple M2 Ultra (192 GB) run MiniMax M2 (230B-A10B)?

87 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q3_K_M it needs about 126 GB of 144 GB usable, with an estimated speed of 54.7 tok/s.

Best quant
Q3_K_M
Generation speed
54.7 tok/s
Prompt processing
1,686 tok/s
First token (1K prompt)
0.6 s
Largest safe context
76K

Download MiniMax M2 (230B-A10B)

Recommended for the Apple M2 Ultra (192 GB): Q3_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 Q3_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 6 days 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.33.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 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.15.0 / 15
Total87.6 / 10087 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

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

Every quantization on the Apple M2 Ultra (192 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 106 GB 144 GB 69.4 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q3_K_M 126 GB 144 GB 54.7 tok/s Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q4_K_M 154 GB 144 GB 35.9 tok/s Runs with offload 77 ptsGreat (A) · 77 of 100 points: Model quality 38.0/45, Memory fit 10.0/25, Speed 14.2/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q5_K_M 177 GB 144 GB 29.7 tok/s Heavy offload 70 ptsGood (B) · 70 of 100 points: Model quality 38.8/45, Memory fit 4.0/25, Speed 12.9/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q6_K 202 GB 144 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
Q8_0 257 GB 144 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)
F16 472 GB 144 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.