Microsoft details Maia 300, its third-generation in-house AI inference chip

What Microsoft announced

Microsoft published a technical description of Maia 300, its next in-house AI accelerator, on 12 October 2026. The post is written by Rani Borkar, president of Azure Hardware Systems and Infrastructure, and Saurabh Dighe.¹ Microsoft says the chip is built for “agentic inference”, including long-context and reasoning-heavy workloads.¹

The design

According to Microsoft, the compute dies are made on TSMC’s N2P process, with memory-controller and I/O functions on separate dies.¹ Each accelerator has eight HBM4 stacks with 288 GB of capacity and 18 TB/s of bandwidth.¹ SiliconANGLE notes that the capacity matches Nvidia’s Rubin accelerator and that the bandwidth is about 20% lower.²

A rack holds 96 accelerators in 24 trays, and up to 128 racks can be joined into a superpod of 12,288 accelerators.¹² Microsoft says liquid cooling removes more than 80% of each rack’s heat.¹

Microsoft’s performance claims

Microsoft claims up to 7x the rack-scale token throughput of Maia 200 and more than 2.5x the performance per watt.¹ SiliconANGLE reports that Microsoft also claims 40% more tokens per megawatt than “leading GPU-based systems”.² These figures have not been independently tested.

Where it will be used

Microsoft says Maia 300 is designed to add capacity for Microsoft Copilot, GitHub Copilot and Microsoft Foundry.¹ SiliconANGLE reports that Microsoft plans to begin production deployment in 2027 and expects the Maia series to become its main source of inference capacity over time.² Microsoft’s post gives no availability date and says more will be shared at Microsoft Ignite, 17–20 November.¹

Why it matters

Like Google and Amazon, Microsoft is building its own AI chips alongside buying from Nvidia and AMD. Maia 200 is already in production, according to SiliconANGLE.²