AI Chips & Infrastructure
Google TPU 8tx and 8i Max expand eighth-gen lineup
The company says the systems target confidential inference and workloads with very large AI context windows.
Illustration of two AI accelerator systems in a data center, representing secure processing and large-context workloads.
Photo: Kronos News
Google announced TPU 8tx and TPU 8i Max, two new systems in its eighth-generation TPU lineup, which now includes four systems: TPU 8t, 8i, 8tx and 8i Max. Google says 8tx is designed for confidential AI inference, while 8i Max targets workloads that need very large context windows. [1]
Google says TPU 8tx uses hardware-level protections to keep data and model weights isolated during processing. The company says 8i Max combines two TPU 8i chips in one package, doubling compute, SRAM and HBM bandwidth compared with TPU 8i. These are company-reported capabilities; the announcement does not provide independent evaluations of the systems’ security or performance. [1]
Editorial notes
Transparency note
AI assisted drafting. Human edited and reviewed.
- AI assisted
- Yes
- Human review
- Yes
- Last updated
Risk assessment
The article relies on Google’s announcement as its sole source.
Sources
Related stories
View all
Topics
About the author
Kronos News Desk covers ai chips & infrastructure and editorial analysis for Kronos News.