PANews, October 12: According to CNBC, Microsoft officially launched its third-generation custom AI accelerator chip, the Maia 300, on October 12, and announced that the Maia series will serve as the primary architecture for running AI models, gradually reducing reliance on NVIDIA GPUs. The Maia 300 is scheduled to enter production in 2027, with each data center rack capable of supporting 96 chips, increasing AI token processing capacity by 7 times per rack and improving token processing efficiency per megawatt by 40% compared to GPUs. Microsoft aims to deploy multi-gigawatt clusters of Maia chips, with Microsoft 365 Copilot being the first to benefit from the performance gains.
Microsoft Unveils Third-Generation AI Chip Maia 300 to Reduce Reliance on NVIDIA
PANewsShare
Summary
On October 12, 2026, Microsoft announced the release of its third-generation AI chip, the Maia 300, designed to reduce dependence on NVIDIA GPUs. The chip will enter production in 2027, with each rack supporting 96 units, delivering a 7x improvement in AI token processing and 40% greater efficiency per megawatt. Multi-exaflop Maia clusters are planned, with Microsoft 365 Copilot set to be the first beneficiary. This AI + crypto news update highlights on-chain developments in the tech and blockchain sectors.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.