Microsoft Unveils Maia 300, Its Most Powerful AI Chip yet - and It Might Make Using Teams, Copilot and Cowork Much Better at Last
The new chip is designed to handle up to seven times more AI tokens per rack and improve efficiency for Microsoft 365 Copilot.
- On Monday, Microsoft unveiled the Maia 300, an AI chip designed to serve as the primary AI inference system for the company's products and services.
- Seeking improved performance, Microsoft designed the architecture to handle emerging workloads including long-context reasoning, latency-sensitive conversational experiences, and multi-step agentic tasks.
- Built on TSMC's N2P process, a full rack of 96 Maia accelerators delivers up to 7 times the rack-scale token throughput of the Maia 200 model.
- Executive Vice President Scott Guthrie said the chip will "deliver 40 percent more tokens per megawatt" compared to leading GPU-based systems, with production starting in 2027.
- Evercore ISI analysts estimate Maia will represent about 10% of Microsoft's chip spending by early 2027, though the company maintains partnerships with Nvidia and AMD for training models.
20 Articles
20 Articles
Microsoft introduced a new artificial intelligence chip, Maia 300, which promises greater processing capacity and lower energy consumption. The company intends to start using it in 2027, reinforcing its own technology bet to reduce the dependence of suppliers such as Nvidia
The Redmond group (state of Washington, northwest) developed its first AI-specific processors, the Maia 100, in 2023, followed by the second generation, the Maia 200, in January. On Monday, he said that the Maia 300, which can allow AI to generate seven times the content obtained with their predecessor, would be operational in 2027. Microsoft now offers an integral architecture around Maia, from the chip to the data center, to the servers and th…
Coverage Details
Bias Distribution
- 56% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
