Microsoft to scale Azure Maia chips to multi-gigawatt deployments from 2027

Microsoft will scale its Azure Maia AI accelerator family to multi-gigawatt deployments starting in 2027, making Maia the primary inference system for Microsoft products and services, Cloud + AI chief Scott Guthrie wrote on October 12.

Maia 200 is already in production. Microsoft says Maia 200 now serves production workloads including Microsoft Copilot and supports the MAI team building next-generation models, with GitHub Copilot and Microsoft Foundry to follow by the end of the year. It runs OpenAI models, Microsoft's own MAI models and leading open-source model families, and is deploying across the United States, Europe and Australia.

Microsoft says Maia 200 delivers up to 1.7 times more tokens per watt than leading GPU infrastructure for built-in AI features in Microsoft Teams, Copilot and Cowork.

Maia 300 targets agents and long context. The next generation is built inference-first for long-context reasoning, latency-sensitive conversations and sustained multi-step agentic tasks. Microsoft expects it to deliver 40% more tokens per megawatt than leading GPU-based systems, and up to seven times the rack-scale token throughput of Maia 200 in a full 96-accelerator configuration.

The rack and chip specs. Each Maia 300 rack holds 96 accelerators within a 167-kilowatt power envelope, with 27.6TB of HBM capacity and 1.7PB/s of aggregate HBM bandwidth. Each accelerator has eight HBM4 stacks providing 18TB/s of peak memory bandwidth within a 950-watt TDP. It uses a new multi-chiplet design, with compute chiplets built on TSMC's N2P process.

Production starts in 2027. Maia 300 will begin production deployments in 2027. Microsoft says it will share more at Ignite 2026 next month.