Google Developing 'Frozen v2' Chip to Run Gemini Models More Efficiently
The Alphabet-owned company is reportedly building a new server chip to address an AI computing capacity crunch that has forced Google Cloud to turn away customers
Google is developing a new server chip designed to run its Gemini artificial intelligence models more efficiently, according to a report from The Information on Monday. Citing people familiar with the matter, the report noted that the technology giant plans to incorporate elements of its Gemini model directly into the hardware itself in a bid to serve its AI models more efficiently to users.[2][3]
The Alphabet-owned company expects the new chip, which has been informally dubbed 'Frozen v2,' to help address a severe AI computing capacity crunch. This capacity shortage has reportedly fueled internal tensions within the company and has even prompted Google Cloud to decline business deals with outside customers.[1][3]
