Microsoft unveils Maia 300 AI chip, aiming to cut its reliance on Nvidia GPUs

Microsoft has announced Maia 300, its third-generation in-house AI chip, which it says will become the "primary AI inference system" for its products, The Verge reported on 12 October 2026. Microsoft says the chip will start rolling out to production AI workloads in 2027, scaling to multi-gigawatt deployments that year. Scott Guthrie, who leads Microsoft's cloud group, told The Verge the company expects Maia 300 to deliver 40 percent more tokens per megawatt than leading GPU-based systems, and that a full 96-accelerator configuration delivers up to 7 times the rack-scale token throughput of Maia 200. The chip is built on TSMC's N2P process and uses a chiplet design that separates compute, memory controller and I/O functions. All of these performance figures are Microsoft's own. Maia 200, announced in January, already runs production workloads including Microsoft Copilot, GitHub Copilot and Microsoft Foundry. Microsoft AI CEO Mustafa Suleyman said running the company's own models on Maia is a critical focus.