Alphabet Developing "Frozen v2" AI Chip for Gemini Models, Shares Rise Amidst Competition

Alphabet shares closed 1.51% higher on Monday after The Information reported the company is developing a new server chip, internally dubbed "Frozen v2," designed to run Gemini models more efficiently.

The chip would permanently embed parts of Gemini's architecture directly into the silicon, reducing the number of calculations and amount of data movement required to answer queries, according to the news outlet.

Alphabet told CNBC in a statement that its teams are "constantly researching and experimenting with new innovations to deliver maximum performance and efficiency for our users and customers" and that "while not every project moves into production, this rigorous exploration is central to our full stack approach."

"By co-designing our hardware and software from the ground up, we ensure our systems are integrated and highly optimized for real-world workloads," continued the statement.

Google engineers project it could serve between six and ten times more tokens per unit of power than the company's newest AI chips, called TPUs, or tensor processing units, The Information said. Frozen would become a more specialized branch of Google's custom-chip portfolio rather than replace its general-purpose TPUs.

According to the report, the company is targeting 2028 for deployment. The project is aimed at easing a major internal compute shortage that has fueled tensions and reportedly forced Google Cloud to turn away outside business.

Just last month, Google agreed to pay SpaceX nearly $1 billion a month to help bridge the gap and meet its enterprise compute commitments.

The trade-off is flexibility. The chip would work with future Gemini models only if Google sticks with the same underlying architecture, according to The Information. Google reportedly currently views Frozen v2 partly as a trial run and does not plan to produce it at the same scale as its TPUs.

Google's AI efforts face a more immediate challenge.

The next Gemini Pro release is delayed and Google has lost several senior researchers to rivals, as Chinese models gain ground with American businesses. Those models now account for 45% of U.S. company token use.

The competitive pressure is only building, with recent new releases from Moonshot AI and Alibaba this weekend narrowing the capability gap.

Google DeepMind chief Demis Hassabis is on Capitol Hill this week to pitch lawmakers on a FINRA-style watchdog for AI that would be federally overseen, largely industry-funded and built to test the most advanced models for national-security risks before release.