InjazAI

Microsoft announced Maia 300, its third-generation in-house AI inference chip, claiming 40 percent more tokens per megawatt than leading GPU-based systems, reducing its reliance on Nvidia.

1 min read

Microsoft unveils Maia 300 AI inference chip, reducing reliance on Nvidia GPUs

What Microsoft announced

FAQ

What is Microsoft's Maia 300?

It is Microsoft's third-generation in-house AI chip, designed to serve as the primary inference system for its products and cloud services.

How does Maia 300 reduce reliance on Nvidia?

By providing an in-house alternative to GPUs for inference workloads, it reduces the need to buy Nvidia chips for those tasks specifically.

When will Maia 300 be available?

According to the announcement, production rollout is set to begin in 2027.

Will MENA enterprises benefit from this chip?

Efficiency gains could eventually affect the cost of cloud AI services available to regional enterprises, but the announcement does not include market-specific details.

Source: The Verge AI

AI-assisted summary of the source above. High-confidence stories publish automatically; others wait for review. Facts that are not in the source are not added.