# MiniMax Releases M3, a Multimodal MoE Model

> The new open-weight model from MiniMax AI combines vision, coding, and reasoning using a Mixture-of-Experts architecture.

Published by The Open Weights on Jun 2, 2026. Canonical: https://theopenweights.com/news/minimax-m3-1lji

## Key facts

- Company: MiniMax
- Model: MiniMax-M3
- Version: M3
- Category: Vision-Language
- Modalities: Vision-Language, Any-to-Any, Code, Reasoning
- License: Other (Open weights, commercial use allowed)
- Active parameters: 23B
- Context window: 1.0M tokens
- Architecture: MiniMaxM3SparseForConditionalGeneration
- Precision: BF16
- Weights size: 854.2 GB
- Significance: major
- Published: 2026-06-02
- Last verified: 2026-07-27
- Hugging Face: https://huggingface.co/MiniMaxAI/MiniMax-M3
- Canonical URL: https://theopenweights.com/news/minimax-m3-1lji

MiniMax AI has entered the open-weight model space with the release of MiniMax-M3, a new multimodal foundation model. Available now on [Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-M3), the model stands out for its sophisticated Mixture-of-Experts (MoE) architecture, a design choice often used to scale models efficiently without a proportional increase in computational cost.

M3 is designed as a versatile system, capable of handling a diverse range of inputs and tasks. Its core strengths lie in its multimodal understanding, allowing it to process and interpret both text and images. Beyond vision, the model is also engineered for coding and complex reasoning, positioning it as a powerful tool for developing more capable AI agents.

The use of an MoE architecture is the key technical detail here. This design activates only relevant neural network pathways—or 'experts'—for a given task. This allows the model to contain a vast number of parameters while keeping inference costs manageable, making powerful capabilities more accessible to a wider range of developers and researchers.

While the model's weights are publicly available, it's released under a custom license rather than a permissive open-source license. This 'open-weight' approach requires users to agree to specific terms for use, reflecting a growing trend where companies release powerful models with some restrictions.

## Get the model

- [Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-M3)
- [Hacker News](https://twitter.com/MiniMax_AI/status/2061266317815296322)

## Sources

- [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3) — Hugging Face, Jun 2, 2026
- [MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities](https://twitter.com/MiniMax_AI/status/2061266317815296322) — Hacker News, Jun 1, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MiniMax Releases M3, a Multimodal MoE Model", The Open Weights, Jun 2, 2026, https://theopenweights.com/news/minimax-m3-1lji