Model reference · open weights
MiniMax-M3 is an open-weight language model from MiniMaxAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters. Highlights: - Native Multimodality: M3 undergoes mixed-modality training from the very first step, enabling deeper semantic fusion across text, image, and video. - Context Scaling via Sparse Attention: M3 introduces MiniMax Sparse Attention (MSA) to improve long context efficiency. M3 delivers 9× prefill and 15× decode speedups compared to M2 at 1M context, reducing per-token compute to 1/20. - Coding & Cowork Capability: M3 achieves frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork. MiniMax Sparse Attention (MSA) M3 is powered by MiniMax Sparse Attention (MSA), a high-performance sparse attention operator designed for million-token contexts. Compared with GQA, MSA dramatically reduces the attention compute and memory footprint while preserving model quality. 📄 Read the technical report: arXiv:2606.13392 · Hugging Face Papers How to Use - MiniMax Agent - MiniMax API M3 supports three reasoning modes through the thinking parameter: - enabled — Reasoning is always enabled. - adaptive — M3 automatically determines when additional reasoning is beneficial. - disabled — Reasoning is disabled to minimize latency and maximize throughput. Local Deployment Download the model: We recommend the following inference frameworks to serve the model: - SGLang - see SGLang cookbook. - vLLM - see vLLM recipes. - Transformers - see Transformers docs. - KTransformers - see KTransformers MiniMax-M3 tutorial. - unsloth - see tutorial - ATOM - see MiniMax-M3 MXFP4/MXFP8 Usage Guide Inference Parameters We recommend the following parameters for best performance: temperature=1.0, topp=0.95. Contact Us Contact us at model@minimax.io.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | MiniMaxAI |
|---|---|
| Type | Language models |
| Parameters (lead) | 427.0B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-06-02 |
| Popularity | 206k downloads / month |
| Likes | 1,509 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MiniMax-M3 | 427.0B | BF16 | ~982.2 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys minimax-m3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-m3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-m3","messages":[{"role":"user","content":"Hello"}]}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗