Google developing Frozen chip with Gemini architecture integrated into hardware

According to The Information as reported by The Next Web, Google is developing a project called Frozen v2 that would bake Gemini's neural-network architecture directly into chip silicon rather than keeping the model in memory. The Information reports the chip could be 6 to 10 times more efficient than Google's latest custom AI chips when measured by tokens served per unit of power. Google has not confirmed the project; deployment is targeted for as early as 2028, and the chip would operate as a new silicon line separate from Google's TPUs rather than a replacement.