Skip to content
Hot storiesContinuously updated

微软推出端侧代码模型MAI-Code-1.1-Flash

1 reports1 reporting sourcesUpdated 5 hours ago

Start here

AI overview

2026年11月5日，微软正式推出代码模型MAI-Code-1.1-Flash，推动137.9B参数规模的大模型落地Windows PC端侧推理。根据报道，MAI-Code-1.1-Flash采用MoE架构，通过混合精度量化技术成功将权重压缩至53.0 GiB。在应用场景方面，该模型已被集成并作为GitHub Copilot的本地端侧模型，实现直接在PC本地完成推理工作。

AI-generated from reports · Updated 4 hours ago

Latest developmentsNov 5 05:13
微软发布137.9B代码模型MAI-Code-1.1-Flash，用于PC端侧推理并集成至GitHub Copilot。

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. Hacker News · AISelected
    Microsoft Unveils MAI-Code-1.1-Flash: A 137.9B Code Model Brought to On-Device Inference on Windows PCs

    Microsoft has released MAI-Code-1.1-Flash, a 137.9B MoE code model, compressing its weights to 53.0 GiB via mixed-precision quantization to serve as a local, on-device model for GitHub Copilot.

Story heat trend

Current heat 9·Comparable peak 10（Nov 5 06:00）·Comparable change, last 24 hours–

02.557.510Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.