Skip to content
Live
Trending storyPast story

MiniMax M3.1 Flash is open source

1 reports1 outlets27 days agoUpdate

The story so far

AI overview

MiniMax and Xiyu Technology have open-sourced the M3.1 Flash model weights, with total parameters of 428B and activation parameters of 23B, to improve inference efficiency. The model is optimized through sparse attention, quantization-aware training, and Power-aware scheduling, processing over 100 trillion tokens within 72 hours of launch.

AI-written from the reports · Updated 27 days ago

Coverage timeline

Follow the coverage to see every side of the story.

23 Oct
  1. ITHome · AI
    MiniMax M3.1 Flash open-source model weights, total parameters 428B

    MiniMax open-source M3.1 Flash model weights, total parameters 428B, activation parameters 23B. Optimized through sparse attention, quantization-aware training, and Power-aware scheduling, inference efficiency is improved, processing over 100 trillion tokens in 72 hours after launch.