Google's 'Frozen v2' Chip Targets Gemini Efficiency

Google is reportedly developing a custom AI chip codenamed Frozen v2, optimized specifically for its Gemini AI models. Sources say it will deliver six to ten times better performance per watt than current silicon, with a planned data center rollout in 2028. The chip aims to cut computational overhead and reduce data movement by storing Gemini models fully on-chip, eliminating slow off-chip memory transfers. It will also likely support operator fusion to speed up processing. Alphabet shares rose 1.5% on the news.