# Google Unveils TPU 8i Max and TPU 8tx: A Dual-Chip TPU and a Confidential TPU

DevFeed: [Google Unveils TPU 8i Max and TPU 8tx: A Dual-Chip TPU and a Confidential TPU](<https://devfeed.tech/articles/google-unveils-tpu-8i-max-and-tpu-8tx-a-dual-chip-tpu-and-a-confidential-tpu-124136.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/09/google-tpu-8i-max-tpu-8tx/>)

Author: Asif Razzaq

Published: 2026-11-09T17:09:54Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Confidential Computing](<https://devfeed.tech/topics/confidential-computing.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [chip](<https://devfeed.tech/tags/chip.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [google](<https://devfeed.tech/tags/google.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [tpu](<https://devfeed.tech/tags/tpu.md>), [tpu-8i-max](<https://devfeed.tech/tags/tpu-8i-max.md>), [tpu-8tx](<https://devfeed.tech/tags/tpu-8tx.md>)

## AI overview

Google's TPU 8i Max and TPU 8tx are new system configurations using existing eighth-generation silicon. TPU 8i Max combines two TPU 8i chips in one package, doubling compute, SRAM and HBM bandwidth while fitting twice the silicon in the existing rack footprint; Google has not published its absolute specifications or HBM capacity. TPU 8tx pairs TPU 8t silicon with 5th Gen AMD EPYC hosts and the TPU 8i Boardfly network to support confidential inference, with Google claiming up to 2x lower latency than TPU 8t and a near-zero security penalty. The excerpt also describes software updates, including TPU Sync's KV-cache tiering across HBM, host DRAM and storage. Its reported latency and time-to-first-token results came from tests on Ironwood (TPU v7x), not the new systems.

## Source excerpt

Google added TPU 8i Max and TPU 8tx to its eighth-generation TPU lineup. TPU 8i Max packs 2 TPU 8i chips per package for long-context agents. TPU 8tx adds hardware confidential inference. Bloomberg reports 2027 availability. The post Google Unveils TPU 8i Max and TPU 8tx: A Dual-Chip TPU and a Confidential TPU appeared first on MarkTechPost.