Google reportedly develops Gemini-specific chip to cut AI inference costs
Frozen v2 could reach servers in 2028, setting a new benchmark for specialized inference-chip startups if Google keeps Gemini's architecture stable.
By Ryan Merket · Published
Primary source: Reuters
Why it matters
Google's reported design moves part of Gemini's economics into silicon, raising the bar for inference-chip founders competing with hyperscalers that control both models and hardware.
Google, founded by Larry Page and Sergey Brin as a Stanford search project, is reportedly developing a server chip that would hardwire parts of Gemini's architecture into silicon. The project amounts to a long-dated bet that Google's AI models can become stable enough to justify hardware designed around them.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.