Modelpublic

unsloth/MiniMax-M3

sourceHugging Faceotherupdated 4mo agoView on Hugging Face

9likes78downloads

Model Card

<div align="center" style="line-height: 1.4; font-size:16px; margin-top: 30px;"> Join Our <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="blank" style="font-size:17px; margin: 2px;"> 💬 WeChat </a> | <a href="https://discord.com/invite/DPC4AHFCBw" target="blank" style="font-size:17px; margin: 2px;"> 🧩 Discord </a> community. </div> <div align="center" style="line-height: 1.2; font-size:16px;"> <a href="https://agent.minimax.io/" target="blank" style="display: inline-block; margin: 4px;"> MiniMax Agent </a> | <a href="https://platform.minimax.io/docs/guides/text-generation" target="blank" style="display: inline-block; margin: 4px;"> ⚡️ API </a> | <a href="https://github.com/MiniMax-AI/cli" style="display: inline-block; margin: 4px;"> CLI </a> | <a href="https://www.minimax.io" target="blank" style="display: inline-block; margin: 4px;"> MiniMax Website </a> </div> <div align="center" style="line-height: 1.2; font-size:16px; margin-bottom: 30px;"> <a href="https://huggingface.co/MiniMaxAI" target="blank" style="margin: 2px;"> 🤗 Hugging Face </a> | <a href="https://github.com/MiniMax-AI/MiniMax-M3" target="blank" style="margin: 2px;"> 🐙 GitHub </a> | <a href="https://www.modelscope.cn/organization/MiniMax" target="blank" style="margin: 2px;"> 🤖️ ModelScope </a> | <a href="https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE" style="margin: 2px;"> 📄 LICENSE </a> </div>

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.

Model Details


Architecture	MoE + MSA (MiniMax Sparse Attention)
Total Parameters	~428B
Activated Parameters	~23B
Experts	128 (4 active per token)
Layers	60
Context Length	1M tokens
Modalities	Text, Image, Video
Precision	bfloat16
Transformers	≥ 4.52.4 (`trust_remote_code=True`)
License	MiniMax Community License

How to Use

—MiniMax Agent
—MiniMax API

M3 supports two reasoning modes:

—thinking — for complex reasoning, agentic tasks, and long-horizon collaboration.
—non-thinking — for latency-sensitive scenarios such as chat and code completion.

Local Deployment

Download the model:

bash

hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3

We recommend the following inference frameworks (listed alphabetically) to serve the model:

SGLang

We recommend using SGLang to serve MiniMax-M3. Please refer to our SGLang Deployment Guide.

vLLM

We recommend using vLLM to serve MiniMax-M3. Please refer to our vLLM Deployment Guide.

Transformers

We recommend using Transformers to serve MiniMax-M3. Please refer to our Transformers Deployment Guide.

ModelScope

You can also get model weights from ModelScope.

Inference Parameters

We recommend the following parameters for best performance: temperature=1.0, top_p=0.95, top_k=40. Default system prompt:

You are a helpful assistant. Your name is MiniMax-M3 and was built by MiniMax.

Tool Calling Guide

Please refer to our Tool Calling Guide.