OpenAI released a new free and open GPT model yesterday that can run on a PC, and now Microsoft is making that easy to do for Windows users. The lightweight gpt-oss-20b model is now available on Windows AI Foundry, and will be coming soon to macOS, too.
You’ll need a PC or laptop with at least 16GB of VRAM, so you’ll need one of the top GPUs from Nvidia or the variety of Radeon GPUs with sufficient VRAM. The gpt-oss-20b model is optimized for code execution and tool use, and Microsoft says it’s “perfect for building autonomous assistants or embedding AI into real-world workflows, even in bandwidth-constrained environments.”
Microsoft has pre-optimized gpt-oss-20b for local inference, and it hints that support for more devices is coming soon. That could mean we see a more optimized version for Copilot Plus PCs at some point in the future, much like how Microsoft has been adding a variety of local AI models to Windows recently.
Microsoft’s speedy addition of OpenAI’s latest model to the Windows AI Foundry comes as Amazon was equally quick to adopt the new open-weight GPT-OSS models for its cloud services. It’s the first time you can run an OpenAI model locally on Windows, but it’s also the first time Microsoft’s biggest cloud competitor has had access to the latest OpenAI models — adding another dynamic to the complicated OpenAI and Microsoft partnership.