Microsoft dates Maia 300 to 2027

Microsoft said on October 12 that it will scale the Azure Maia family to multi-gigawatt deployments starting in 2027, and that Maia will be the primary inference system for Microsoft products and services. Maia 300, the company says, begins production deployments in 2027.

The efficiency claim is Microsoft’s expectation, not a measured result from this desk. By improving efficiency across the system, Microsoft says it expects Maia 300 to deliver 40 percent more tokens per megawatt than leading GPU-based systems. In a full configuration of 96 accelerators, Microsoft says it delivers up to seven times the rack-scale token throughput of Maia 200.

The same post says Maia 200 is already in production, including for Microsoft Copilot, and that GitHub Copilot and Microsoft Foundry are to follow by the end of 2026. Microsoft says Maia 200 is deploying in the United States, Europe, and Australia, and delivering up to 1.7 times more tokens per watt than leading GPU infrastructure for built-in AI in Teams, Copilot, and Cowork.

On the new chip, Microsoft says the compute chiplets use TSMC’s N2P process. A Maia 300 rack, in the company’s description, holds 96 accelerators inside a 167-kilowatt power envelope, with 27.6 terabytes of high-bandwidth memory and 1.7 petabytes per second of aggregate memory bandwidth. Eight HBM4 stacks, Microsoft says, provide 18.0 terabytes per second of peak memory bandwidth inside a 950-watt power limit.

The post is a product announcement. It does not say what the chip will do to anyone’s share price, and this desk will not supply that number.