GoKawiilGoogle unveils TPU 8tx and TPU 8i Max chips for confidential AI and larger workloads
Google introduced two new tensor processing units, TPU 8tx and TPU 8i Max, expanding its eighth-generation chip lineup launched in April. TPU 8tx, co-designed with AMD, is built for confidential training and inference, embedding security at the hardware level to protect data and model weights during use. TPU 8i Max combines two TPU 8i inference chips into one package, doubling memory, processing power and bandwidth.
GoKawiil's interpretation of the reporting above, not reported fact.
The release suggests Google is pushing deeper into custom silicon to cut reliance on outside chipmakers for its cloud business, joining Microsoft, Amazon, OpenAI and Anthropic in building proprietary AI hardware. This expansion arrives as Nvidia's CEO Jensen Huang has reportedly acknowledged challenges, which could signal shifting competitive dynamics in the AI chip market, though the long-term impact remains uncertain.
- Google launched TPU 8tx and TPU 8i Max, extending its eighth-generation chip family.
- TPU 8tx, built with AMD, targets confidential AI training and inference with hardware-level security.
- TPU 8i Max merges two TPU 8i chips to double memory and processing capacity for larger AI workloads.
Source: techcrunch.com — Ram Iyer, 2026-11-10
Published there as: “Google broadens its AI hardware portfolio with two new specialized chips”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.