# Microsoft — Bringing local models and sandboxed tools to Windows and GitHub Copilot

- Company: Microsoft (microsoft.com)
- Announced: 2026-10-07T18:00:00+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://commandline.microsoft.com/local-models-sandboxed-tools-github-windows/
- Record: https://forck.live/items/19121-bringing-local-models-and-sandboxed-tools-to-windows-and-github-copilot
- Subject: Foundry / Responsible AI
- Models affected: MAI Code 1.1 Flash, MAI Code 1.1 Flash Quantized on Device

Microsoft announced that GitHub Copilot will gain the ability to automatically route coding tasks between local on-device models and cloud-scale models, starting with the quantized MAI Code 1.1 Flash model on NVIDIA RTX Spark Windows PCs. The local model achieves 70.80% on SWE-Bench Verified and 66.29% on Terminal-Bench 2.1 with a peak memory usage of 75.5GB at 256k context. Developers can let Copilot orchestrate model placement automatically or explicitly select a local model.

## Evidence

Verbatim from https://commandline.microsoft.com/local-models-sandboxed-tools-github-windows/:

> With our first shipping version of MAI Code 1.1 Flash on Surface Laptop Ultra we achieve the following performance at different context lengths, with peak memory usage of 75.5GB at 256k context. At 64k and 128k context, prompt-processing throughput reaches 923.5 and 769.8 tokens per second, respectively.

---

Record: https://forck.live/items/19121-bringing-local-models-and-sandboxed-tools-to-windows-and-github-copilot
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md