Post-Cutoff

Microsoft: ‘Introducing Maia 300, Microsoft’s next-generation accelerator’

Microsoft @MicrosoftX

Why it matters

Microsoft’s corporate announcement post for Maia 300.

Summary

Posted Oct 12, 2026 (13:16 UTC). Microsoft’s main account: ‘Introducing Maia 300, Microsoft’s next-generation accelerator. Building on the magic of Maia 200, it delivers 40% more inference tokens per megawatt compared to leading GPU-based systems, and up to 7x the rack-scale token throughput of Maia 200.’ Links to aka.ms/Maia300. Both figures are Microsoft’s own.

Metrics as of 2026-10-13 via api.fxtwitter.com: 116,916 views, 1,452 likes, 193 reposts.

Archived text

Introducing Maia 300, Microsoft’s next-generation accelerator. Building on the magic of Maia 200, it delivers 40% more inference tokens per megawatt compared to leading GPU-based systems, and up to 7x the rack-scale token throughput of Maia 200. It’s another step toward rethinking innovation and unlocking new possibilities.

Discover how Maia 300 will help co-create what’s next for Microsoft’s infrastructure and technology: http://aka.ms/Maia300

Source: x.com/Microsoft/status/2109634232163471782Archived 2026-10-13 via fxtwitter (unofficial).Counts: 117,608 views, 1,456 likes, 193 reposts, 120 replies (at fetch time)Media: image

Cited in

  1. Chips & compute 104 days after the cutoff

    Microsoft announces Maia 300, its third in-house AI chip, and plans multi-gigawatt Maia deployments from 2027