Google announces TPU 8tx and TPU 8i Max systems
Google announced TPU 8tx for secure, confidential inference and small-scale training, and TPU 8i Max for massive context windows and high compute density per rack. TPU 8tx uses TPU 8t silicon and 5th Generation AMD EPYC hosts, while TPU 8i Max combines two TPU 8i chips and provides double the compute, SRAM and HBM bandwidth of TPU 8i. The eighth-generation TPU portfolio now includes four systems, and the article discloses no financial results or guidance.
Key takeaways
TPU 8tx provides hardware-level confidential computing for regulated enterprise and government workloads.
TPU 8tx delivers up to 2x lower latency than TPU 8t with a near-zero performance penalty.
TPU 8i Max combines two TPU 8i chips and provides double the compute, SRAM and HBM bandwidth of TPU 8i.
Google said this is the first time it has introduced four TPU systems in a single year.
Google reported nearly 100 TPU customers, including frontier labs, trading firms, retailers and universities.
The announcement includes PyTorch support, open-source development tools, TPU Sync, and general availability of Cloud Pathways and GKE dynamic slicing.
Google scheduled a broadcast about the new systems for 2026-11-09 at 9 a.m. PT.
Key metrics
Primary source
TickerStar generated this brief from an official company, investor-relations, earnings-call, or regulatory source. Review the primary material before making an investment decision.
Open Investor relationsFollow GOOGL in real time
Get material earnings, filing, IR, and earnings-call alerts by email.