Microsoft announces Maia 300 AI chip, rolling out in 2027
Microsoft's third-generation in-house AI chip is built for running AI models and will reach production workloads next year.
Microsoft is making its own computer chip to run AI faster and with less electricity. It will start working in Microsoft's data centers next year.
Hype check
The noise matches the real change.
Our editorial opinion, based on the sources below. How we score
Your call: hype or real?
Real = it will matter in daily use. Hype = louder than it is. One vote, and it can’t be changed.
Our view and readers’ views are opinions, not statements of fact about a product.
Why it matters
Microsoft wants its own chips to be the main system for running AI in its products, which can lower cost and power use.
Worth a look: big tech is building its own AI chips.
The details
- Microsoft says Maia 300 should give 40% more per megawatt than leading GPU-based systems.
- In a 96-accelerator setup it is said to deliver up to 7x the rack-scale throughput of Maia 200.
- It is built on TSMC's N2P process with separate compute, memory and I/O parts.
- Microsoft plans multi-gigawatt Maia deployments starting in 2027.
- Maia 200, announced in January, already runs Copilot and other Microsoft services.
Receipts
One trusted outlet reports it. Not confirmed yet. Open the sources and check us.
Written with the help of AI tools and checked against the sources above. How we work
See a mistake? Tell us and we’ll fix it.
