Microsoft to scale Maia silicon to multi-gigawatt in 2027, Maia 300 promises 40% more tokens per MW
shashib · x · 2026-10-13
Microsoft announced on Oct 12 that it will scale the Azure Maia chip family to multi-gigawatt deployments starting 2027 and make Maia the primary inference system for its own products. EVP Scott Guthrie posted the plan; Satya Nadella called it the company's biggest bet on its own silicon.
- Maia 200: in production and deploying across the US, Europe and Australia, already serving Copilot workloads; up to 1.7x more tokens per watt than leading GPU infrastructure for Teams, Copilot and Cowork
- Maia 300: production deployments begin 2027, 40% more tokens per megawatt than leading GPU systems; a full 96-accelerator, 167 kW rack delivers up to 7x the rack-scale token throughput of Maia 200
The author argues owning the silicon is as strategic as it gets: without the hardware there is no software.
Related event: Microsoft Unveils Maia 300, Targeting Multi-Gigawatt AI Inference by 2027(14 posts)→
More from Infra
- Rodolfo Rosini on 2040: cheap compute everywhere, devices jumping orders of magnitude — MikePFrank · 2026-10-13
- AI inference chips are a $225bn market: Vaire on why startups avoid silicon and its Nvidia-adjacent plan — MikePFrank · 2026-10-13
- Vaire CEO Explains Reversible Computing Chips That Recycle Energy Like a Tide Mill — MikePFrank · 2026-10-13
- China's $165B AI buildout rests on $11B model revenue and 4% of Nvidia's chip output — demian_ai · 2026-10-13
- New llama.cpp release adds multimodal model support and Metal performance gains — vboykis · 2026-10-13
- Broadcom optical roadmap: TH6 hits 102.4T in 2026, next-gen OCI by 2028 — firstadopter · 2026-10-13