Google has added two systems to its eighth-generation Tensor Processing Unit (TPU) line-up: TPU 8tx, built for secure and confidential AI inference, and TPU 8i Max, a dual-chip system for very long context windows. Amin Vahdat, Senior Vice President and Chief Technologist, AI and Infrastructure at Google, announced them on 9 November 2026, making it four new TPU systems in a single year.

The launch lands as India debates how sensitive public and regulated workloads should run AI, including the government’s reported push for indigenous AI models in defence and critical sectors.

What Google TPU 8tx does

TPU 8tx is aimed at regulated enterprises and governments that run frontier or proprietary models and autonomous agents on their most sensitive data. Data is usually encrypted at rest and in transit but must be decrypted in memory while it is processed. Google said TPU 8tx builds protection into the hardware so that data and model weights stay isolated even while in use.

• It uses the same silicon as TPU 8t and pairs it with 5th Generation AMD EPYC CPU hosts.
• It runs on Google’s low-latency Boardfly network and offers up to 2x lower latency than TPU 8t, with what Google called a near-zero performance penalty.
• Teams can fine-tune on private data, distil large models into smaller ones and train agents with reinforcement learning without moving data between clusters.

TPU 8i Max and the memory wall

TPU 8i Max places two TPU 8i chips on one package. Google said it delivers double the compute, double the SRAM and double the HBM memory bandwidth of TPU 8i, so large multi-agent and long-video workloads do not stall. Because it fits twice the silicon into the existing rack footprint, data centres can pack more compute per square foot and per watt.

The two systems join TPU 8t for large-scale training and TPU 8i for real-time reasoning, which Google introduced at Google Cloud Next in April 2026. Vahdat wrote that TPUs now have nearly 100 customers, including frontier labs, trading firms, retailers and universities, and that some customers can deploy TPUs directly in their own data centres.

Why it matters for Indian enterprises and government

Confidential computing speaks directly to banks, insurers, hospitals and government departments that want to use frontier models without exposing citizen or customer data. It also fits a wider shift towards controlled AI compute in India, seen in moves such as NSE’s on-premises GPU build-out with liquid cooling and India-only inference for Kimi K3 on Amazon Bedrock.

At the same time, India is working on its own silicon. MeitY is targeting an indigenous GPU chip in about 24 months, and startups such as Agrani Labs are raising funds for AI inference chips. Google’s post did not give India-specific pricing or availability for the new systems.

Google also said its open-source TorchTPU work lets PyTorch code and Hugging Face models run natively on TPUs, which lowers the switching cost for Indian developer teams that build on PyTorch today. The full details are in Google’s TPU 8tx and TPU 8i Max announcement and on the Google Cloud TPU page.

Key takeaways

• Google announced TPU 8tx and TPU 8i Max on 9 November 2026, its third and fourth eighth-generation TPU systems this year.
• TPU 8tx keeps data and model weights protected while in use, for regulated enterprises and governments.
• TPU 8i Max doubles compute, SRAM and HBM bandwidth over TPU 8i for long-context agent workloads.

FAQ

What is Google TPU 8tx?

TPU 8tx is a Google AI accelerator system for confidential inference and small-scale training, paired with AMD EPYC hosts so data stays protected while it is processed.

How is TPU 8i Max different from TPU 8i?

TPU 8i Max combines two TPU 8i chips in one package, giving double the compute, SRAM and HBM bandwidth in the same rack space.

Is TPU 8tx available in India?

Google’s 9 November announcement did not list India-specific pricing or availability.

Featured image: Google’s TPU 8tx and TPU 8i Max systems. Image: Google

Be a part of Elets Collaborative Initiatives. Join Us for Upcoming Events and explore business opportunities. Like us on Facebook , connect with us on LinkedIn and follow us on Twitter.

"Exciting news! Elets technomedia is now on WhatsApp Channels Subscribe today by clicking the link and stay updated with the latest insights!" Click here!