Microsoft has introduced a local edition of MAI-Code-1.1-Flash that runs on Windows PCs without server access. The model requires substantial memory and is coming to GitHub Copilot in experimental preview by the end of October, starting with Nvidia RTX Spark PCs.

Wrong: Claude Opus 5.5's 87.6% and GPT-6 Astra's 87.3% Terminal-Bench 2.1 scores read as Microsoft's own figures. Right: those scores come from Vals AI's Terminal-Bench 2.1 leaderboard, which uses a different test setup; Microsoft reported only its own model's scores (62.9% cloud, 66.3% local).
Wrong: said Microsoft recommends more than 120 GB of video memory to run the local MAI-Code-1.1-Flash. That figure came from Frandroid, not Microsoft. Right: Microsoft says the local model's memory use peaks at 75.5 GB at its full 256K context, so it effectively needs a 128 GB RTX Spark machine.
Wrong: said MAI-Code-1.1-Flash activates 5 billion parameters per step and was "confirmed in development" for GitHub Copilot, and gave only the cloud model's 62.9% Terminal-Bench 2.1 score. Right: Microsoft says the model has 137 billion total and 6.8 billion active parameters; the local version comes to GitHub Copilot in experimental preview by the end of October; on Terminal-Bench 2.1 the cloud model scored 62.9% and the local version 66.3%.
Microsoft says memory use peaks at 75.5 GB at the full 256K context, so it effectively needs a 128 GB RTX Spark machine.
Computations occur on the device itself, so Microsoft states users will not be billed for tokens.
Tap a lens to see what this story means for you.
Liked this? The Brief brings you the whole day in tech, verified, every morning.
Two minutes, free forever. What's in The Brief →
See what’s happening right now
The Feed runs all day — short, verified briefs the moment they break.
Open the FeedFollow @thecircuitry_
Every story we publish, as it happens. No noise between.
Reader-supported
The Circuitry is a passion project I've always wanted to build, and I love the work behind it.
Running it costs real money. APIs, hosting, time. To keep improving the site and growing this into something useful for everyone, those costs have to be covered.
Any contribution is appreciated. If not, no pressure. Thanks for reading.
At its Windows and Surface event, Microsoft opened preorders for the $2,599 Surface Laptop Ultra and the $5,999 Surface RTX Spark Dev Box, and said Copilot will be able to use files and act across Windows in the coming months.
Microsoft says Copilot on Copilot+ PCs will be able to use files and recent activity on your PC, take actions across Windows, and tap local AI models, with your permission. The features are expected to start rolling out in the coming months.
Microsoft demonstrated hybrid intelligence on Windows that runs AI models from 70 billion to 284 billion parameters locally. The approach keeps data on-device, supports offline use, and switches to cloud models for heavier tasks.
Microsoft Dataverse is affected by critical vulnerability CVE-2026-88131, which allows remote code execution. The flaw scores 9.8 on CVSS; Microsoft says it has already fully mitigated it and customers have nothing to patch.
Anthropic has launched the Anthropic Cyber Mission to support defenders of critical infrastructure and open-source software with models, engineers, and tools. The initiative starts with the Critical Infrastructure Defense Program and free OSS Scanner amid ongoing challenges in verifying and fixing vulnerabilities.