Overview
MiniMax-M3 is an open-weight large language model from MiniMaxAI, the Chinese AI lab behind the MiniMax series.
- License: Other
- Context length: 1M tokens
- Languages: Multilingual
- Minimum hardware: ~239 GB VRAM
- Strengths: reasoning, coding and on-device inference
Highlights
- Native multimodality — mixed-modality training from the first step fuses text, image, and video.
- Sparse attention scaling — MiniMax Sparse Attention gives 9x prefill and 15x decode speedups at 1M context.
- Coding & cowork — frontier-level performance on long-horizon agentic benchmarks.
- 1M context — reads entire codebases or long document sets in one pass.
What it is good at
MiniMax-M3 was built around coding and agentic work, with reasoning and vision as first-class capabilities. Three things it handles well:
- Coding and agentic tasks — it posts strong autonomous-agent scores (around 59% on SWE-Bench Pro in MiniMaxAI's reporting), so it can plan, edit across files, and run multi-step tool loops.
- Long-context reasoning — the 1M-token window plus sparse attention lets it read entire codebases or long document sets in one pass and reason over them with the thinking mode.
- Vision and visual understanding — being natively multimodal, it reads screenshots, diagrams, and UI mockups alongside text, which suits debugging from an image or extracting data from a chart.
Running it locally
This is a heavy model. At 427B parameters even quantized builds run large: the smallest GGUF quant lands near 128GB, and a comfortable quant wants 130GB or more of RAM or unified memory. A 512GB Mac Studio M3 Ultra can drive long generations; multi-GPU servers use 8-way tensor parallelism. The full 1,048,576-token context also needs room for the KV cache on top of the weights.
huggingface-cli download MiniMaxAI/MiniMax-M3
Once the weights are local you can serve them through vLLM, SGLang, or llama.cpp, or load the model in Atomic Chat with one click and start chatting without touching a config file.
License
MiniMax-M3 ships under a custom "other" license rather than a standard OSI license, so the exact terms come from MiniMaxAI's own agreement on the model's Hugging Face page. The weights are openly downloadable for local and offline use; check that license text before any commercial deployment to confirm what redistribution and production use it permits.