Tag: Microsoft Foundry
-
Qwen3.8-27B Foundry Local Setup: Run Copilot’s Coding Agent on Your Own GPU
Microsoft showed how to run Qwen3.8-27B on your own PC and plug it into GitHub Copilot. Here is the GPU you need and how to set it up.
-
MAI-Base-2 Explained: Microsoft’s 2.8T Model Is Trained, but You Can’t Use It Yet
Microsoft finished pre-training its 2.8-trillion-parameter MAI-Base-2. Here’s what it is, what Microsoft claims, and why there’s still nothing to download.
-
Microsoft Decision-1 Explained: The $0.042 AI Model That Scores Choices, Not Text
Microsoft just put a fast, cheap AI model in Foundry that picks answers instead of writing them. Here is the price, the claims and how to test it.