Model Releases

MiniMax M3 released: frontier coding, 1M context and native multimodality in one

Original title:MiniMax M3:前沿 Coding 能力、1M 上下文、原生多模态,一个模型全给你

AI summary

MiniMax released the M3 model, which uses a new sparse attention architecture called MSA, supports a 1M context window, and natively supports image and video input as well as desktop computer operation. It is the first open-source model in China to combine all these features.

Key Takeaways

  • MiniMax released the M3 model,which uses a new sparse attention architecture called MSA,supports a…
  • and natively supports image and video input as well as desktop computer operation.
  • It is the first open-source model in China to combine all these features.

Quick Facts

Published
Updated
Source
公众号:MiniMax(稀宇科技)
Category
Model Releases
AI score
78
Read the original Read the full article at the original source
Why it matters

M3在复现论文和CUDA优化中的长程自主迭代,将模型评估从单轮得分推进到真实协作场景,为衡量Agent Coding能力提供了更具参考价值的维度。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: MiniMax M3 released: frontier coding, 1M context and native multimodality in one. June 1, 2026. https://new.nat6.net/en/news/cmsdu3hys0161rofz8hy0d3jc/

View all →