Microsoft Unveils Maia 300 Chip to Reduce Nvidia GPU Dependence

The new Maia 300 chip is scheduled to roll out to production AI workloads starting in 2027.

Microsoft is introducing its third-generation Maia in-house AI chip today, designed to act as the “primary AI inference system” for the company's products and services. The Maia 300 improves the cost and efficiency of running AI workloads in the cloud while handling advanced reasoning models and agentic tasks more effectively.

Maia 300 will begin production deployment in 2027, with efficiency as a key design goal. Scott Guthrie, executive vice president of Microsoft's cloud group, stated, “We expect Maia 300 to deliver 40 percent more tokens per megawatt compared to leading GPU-based systems,” and noted that in a full 96-accelerator configuration, it delivers up to 7x the rack-scale token throughput of the Maia 200.

These efficiency improvements will allow Microsoft to rely primarily on its own AI chips rather than those from NVIDIA and AMD. Guthrie added, “We will scale our Azure Maia family to multi-gigawatt deployments starting in 2027, making Maia the primary AI inference system for Microsoft products and services.”

Maia 300 is the successor to the 200, which was announced only in January. The Maia 200 is already running production AI workloads across Microsoft, including Microsoft Copilot, GitHub Copilot, Microsoft Foundry, and the company's own AI models. Guthrie noted that “Maia 200 is the best performing AI infrastructure in our fleet, measured in real world metrics for AI services.”

Maia 300 is a complete system designed for new types of AI workloads, including long-context reasoning, latency-sensitive conversational experiences, and sustained, multi-step agentic tasks.

Microsoft is using a new chiplet architecture to achieve its efficiency gains. Built on TSMC’s N2P process node, the latest Maia 300 architecture separates compute, memory controller, and I/O functions. “This increases the silicon area dedicated to compute performance and allows each function to use the technology best suited to its role,” the Azure hardware and infrastructure team explained.

The Maia 300 is also vital for Microsoft's own model work, potentially helping the company catch up with Google DeepMind, OpenAI, and Anthropic. Microsoft AI CEO Mustafa Suleyman remarked, “We have to work across the full stack, all the way down to the silicon. At that scale we need a platform that we own, and that we co-design with our models. That’s why running our Microsoft AI models on top of the Maia chip is a critical focus for our team.”