Check my GPU

LLMs ·

MiniMax M3 (427B)

Parameters
427B (25.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
minimax-community
Released
2026-06

How to run it

Ollama

Ollama offers this only as a cloud model (it runs on Ollama’s servers, not your machine). To run it locally, use the GGUF files below.

Quantized files · GGUF

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

huggingface.co/unsloth/MiniMax-M3-GGUF (opens in a new tab)

ollama run hf.co/unsloth/MiniMax-M3-GGUF

Original weights · Hugging Face

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

huggingface.co/MiniMaxAI/MiniMax-M3 (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-M3 (opens in a new tab)

git clone https://github.com/MiniMax-AI/MiniMax-M3

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: active parameters estimated from the expert layout (about 25B).

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 171 GB 172 GB 175 GB GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
Q3_K_M Low 209 GB 211 GB 214 GB GGUF · folder (opens in a new tab)
Q4_K_M Good 260 GB 262 GB 265 GB GGUF · folder (opens in a new tab)
Q5_K_M High 303 GB 305 GB 308 GB GGUF · folder (opens in a new tab)
Q6_K High 350 GB 352 GB 355 GB GGUF · folder (opens in a new tab)
Q8_0 Very high 453 GB 454 GB 457 GB GGUF · folder (opens in a new tab)
F16 Full 854 GB 856 GB 859 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for MiniMax M3 (427B)

Grade · points Hardware Quant Memory Speed Fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 15.0/15 Apple M3 Ultra (512 GB) Q4_K_M 293 GB / 384 GB 17.3 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 12.6/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q2_K 188 GB / 192 GB 28.4 tok/s Tight fit

Check it on your own hardware

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.