Microsoft bets big on custom silicon: Maia 300 claims 40% more tokens per watt, multi-gigawatt deployments
TinfoilTricorn · x · 2026-10-12
Microsoft CEO Satya Nadella announced the company's biggest bet yet on its own silicon: starting next calendar year, Microsoft will scale its Maia family to multi-gigawatt deployments as the primary inference system for its own products and services, and introduced Maia 300, claiming 40% more tokens per watt than leading GPU-based systems.
Slide specs: multi-chiplet N2P process, 13.8 PFLOPS FP4 / 6.9 PFLOPS FP8, 950W SoC TDP, 8x HBM4 stacks (288GB, 18TB/s), 3.2 TB/s bi-directional scale-up bandwidth, 96 Maias per rack, 12k accelerators per scale-up domain over a two-tier Ethernet fabric.
Related event: Microsoft Unveils Maia 300, Betting Big on In-House AI Silicon(10 posts)→
More from Infra
- Robotics research goes big: one work reportedly used 64 H200 GPUs — chris_j_paxton · 2026-10-13
- US needs allied datacenters it can't build at home, argues Foreign Policy piece — abhiadesai · 2026-10-13
- Huawei says Ascend has passed Nvidia in China share, deploys 256K-GPU super node — pstAsiatech · 2026-10-13
- CoreWeave Launches Model Distillation Preview to Cut Frontier-Model Costs — altryne · 2026-10-12
- AWS guide: deploy llama.cpp decision models on SageMaker, GPU cuts tail latency 32x — AWS ML Blog · 2026-10-12
- NVIDIA Opens Vera Rubin Rack Designs, Publishes Open Standards for Next-Gen AI Factories — elonmusk · 2026-10-12