Microsoft puts Maia 200 AI accelerator into volume production
11/18/2026 — 11/18, 08:20·1 sources (all)·1 reports (all)
Key takeaways
- At Ignite 2026, Microsoft said its second-generation in-house AI accelerator, Maia 200, has entered volume production and is now running its…
Background & analysis
On November 17, 2026, at the Ignite 2026 event, Microsoft announced that its second-generation custom AI accelerator, Maia 200, has entered volume production and has begun running Microsoft's largest-scale frontier AI models in data centers. Microsoft stated that, compared with leading GPU infrastructure, Maia 200 delivers up to 1.7x more tokens per watt for built-in AI features in Microsoft Teams, Copilot, and Cowork.
According to an IT之家 report published on November 18, 2026, Maia 200 is a custom chip designed for AI inference. It is built on TSMC's 3-nanometer process and features FP4 and FP8 tensor cores, 216GB of HBM3e memory, and 272MB of on-chip SRAM. A single chip delivers more than 10 petaFLOPS of compute at FP4 precision, and clusters can scale to as many as 6,144 accelerators via Ethernet.
The chip has already been deployed in the United States, Europe, and Australia, where it is supporting production workloads such as Microsoft Copilot. Support for GitHub Copilot and Microsoft Foundry is expected to follow gradually. Microsoft also plans to expand the Azure Maia system to multi-gigawatt-scale deployments in 2027.
AI-generated from 1 reports · updated 23 minutes ago
- Heat index
- 98
- All sources
- 1
- All reports
- 1
- First seen
- 57 minutes ago
Reports on this story headlines open the original
Microsoft said at Ignite 2026 that its second-generation Maia 200 AI accelerator has entered volume production and is now running its largest frontier models in data centers, IT之家 reported. Microsoft claims up to 1.7x more tokens per watt than leading GPU infrastructure on built-in AI features such as Teams, Copilot and Cowork. The chip is deployed in the US, Europe and Australia, with GitHub Copilot and Microsoft Foundry support to follow.
IT之家AI score 53
Other stories people are talking about
- Heat index 1423SurgeGPT-6.2 Astra and Sol Now Available on ChatGPT, API and Perplexity16 sources
- Heat index 1337SurgeNvidia chairman confirms no plan to bring Jensen Huang back as CEO15 sources
- Heat index 1232Nvidia board establishes national security and export control committee24 sources
- Heat index 1054RisingAnthropic Plans to Raise IPO Price, Valuation May Hit $1.6 Trillion13 sources
- Heat index 969California Sues OpenAI Over Agent Intrusion Into Hugging Face19 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

