Hugging Face · #184

MiniMaxAI/MiniMax-M3

MiniMaxAI/MiniMax-M3 is a 427B image-text-to-text model on Hugging Face. Run locally: llama-cli -hf MiniMaxAI/MiniMax-M3 or ollama run hf.co/MiniMaxAI/MiniMax-M3. 1,589 Hugging Face likes (#184 in this directory).

Model
https://huggingface.co/MiniMaxAI/MiniMax-M3
Author
MiniMaxAI (org)
Likes
1,589
Downloads (30 days)
208,764
Task
image-text-to-text
Library
transformers
License
minimax-community
Parameters
427B
Gated
No
Created
2026-06-02
Last modified
2026-07-23
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf MiniMaxAI/MiniMax-M3

Ollama

ollama run hf.co/MiniMaxAI/MiniMax-M3

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run MiniMaxAI/MiniMax-M3 only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology