Today for AI
HOT RADAR
llmHEAT 11.1°

AI CURATED HOT STORY · 10/23/2026

MiniMax Open-Sources M3.1 Flash Weights with 428B Total and 23B Active Parameters

1 reports archived1 independent sourcesupdated 10/23/2026, 09:08:08
Synthesis & Latest Updates
1 Sources Cross-Validated

MiniMax has open-sourced the weights for its M3.1 Flash model, featuring a sparse architecture with 428B total and 23B active parameters. The release enhances inference efficiency through full-model sparse attention, quantization-aware training, and power-aware scheduling, with day-one support from major chip vendors and cloud platforms.

LATEST/MiniMax has open-sourced the weights for its M3.1 Flash model, featuring a sparse architecture with 428B total and 23B active parameters. The release enhances inference efficiency through full-model sparse attention, quantization-aware training, and power-aware scheduling, with day-one support from major chip vendors and cloud platforms.

HEAT TRENDHourly heat curve

3 fully observed hours
Now
11.1
Peak
11.810:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·88 pts
    • M3.1 Flash features 428B total parameters but only 23B active, representing an efficient sparse architecture
    • Incorporates full-model sparse attention, QAT, and power-aware scheduling to maximize hardware utilization
    • Secured day-one support from a broad ecosystem including Huawei Ascend, NVIDIA, vLLM, and others upon release
MiniMax Open-Sources M3.1 Flash Weights with 428B Total and 23B Active Parameters | Today for AI