Microsoft's Maia 300 AI chip: 40% more tokens per megawatt, production in 2027
Article timeline
The articles in this story. Times are ET.
Microsoft@MicrosoftOfficialMicrosoft unveils Maia 300 accelerator, claiming 40% more tokens per megawattAIMicrosoft introduces Maia 300, its next-generation AI accelerator, which it says delivers 40% more inference tokens per megawatt than leading GPU-based systems. Microsoft also says Maia 300 offers up to 7x the rack-scale token throughput of its predecessor, Maia 200.
Tom Warren@tomwarrenXMicrosoft's Maia 300 AI chip to roll out to production workloads in 2027AITom Warren reports that Microsoft's new Maia 300 AI chip will start rolling out to production AI workloads in 2027. He says the chip makes Microsoft less reliant on Nvidia's GPUs.
- CNBC · TechnologyNewsMicrosoft to rely more on its Maia chips for AI inference, reducing Nvidia dependence
AIMicrosoft says its third-generation Maia 300 accelerator will mainly handle incoming AI requests, reducing reliance on Nvidia GPUs. The chip fits 96 units per rack and runs up to seven times more AI tokens per rack than GPUs, with 40% more tokens per megawatt. Production starts in 2027, and Nvidia and AMD remain central to model training, while Maia chips are not rented to outside customers.
- The Verge · AINewsMicrosoft announces Maia 300 AI chip, aiming to rely less on Nvidia and AMD GPUs
AIMicrosoft announces its third-generation Maia 300 in-house AI chip, designed as the primary inference system for its products and services. Scott Guthrie says it delivers 40 percent more tokens per megawatt than leading GPU-based systems, with rollout to production starting in 2027. The chip uses a chiplet architecture built on TSMC's N2P process node.