# Google made four TPUs this year, and the rest of us get an interest form (slim) > Vlad Cealicu on TPU 8tx and TPU 8i Max, the third and fourth eighth-generation TPUs Google announced on 9 November 2026. More competition for Nvidia is good for everyone running agents, but the frontier labs, governments and regulated enterprises get the chips first, and the TPU page still says coming soon. - Full: https://www.anchorterminal.com/blog/google-tpu-8-four-chips-and-an-interest-form.md (~2,550 tokens) · this version ~1,230 tokens · JSON https://www.anchorterminal.com/blog/google-tpu-8-four-chips-and-an-interest-form.json · canonical https://www.anchorterminal.com/blog/google-tpu-8-four-chips-and-an-interest-form - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10 - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) By Vlad Cealicu, 10 November 2026. 839 words, about 4 min to read. Google announced TPU 8tx and TPU 8i Max yesterday, the third and fourth systems in its eighth generation of TPUs, after TPU 8t and TPU 8i in April, and it's the first time Google has brought out four TPU systems in one year [[1]](#ref-1). ## What they announced TPU 8tx is the same silicon as TPU 8t, paired with AMD EPYC hosts, with the protection built into the hardware so the data and the model weights stay isolated while they're being used. TPU 8i Max is two TPU 8i chips on one package, with double the compute, the on-chip memory and the memory bandwidth of a TPU 8i, in the same rack space, for very long contexts and dozens of agents working on one codebase at once [[1]](#ref-1). ## Why it's good I think Nvidia's advantage was never only the chip, it's that everything people write runs on Nvidia first. Google also wrote up Agent Compute Engine in October, the sandbox its own agents run in. ## Who gets them first In April Google said TPU 8t and TPU 8i would be generally available later this year [[6]](#ref-6). Someone has them though. 2026 1. **31 March** (lease). Broadcom signs the lease for customer-hosted TPU8i pods, with Anthropic as guarantor [[9]](#ref-9) 2. **22 April** (announced). TPU 8t and TPU 8i, generally available "later this year" [[6]](#ref-6) 3. **20 October** (open). TorchTPU open-sourced, with vLLM and SGLang backends [[4]](#ref-4) 4. **22 October** (interest form). Agent Compute Engine, a preview "in the coming months" [[5]](#ref-5) 5. **9 November** (announced). TPU 8tx and TPU 8i Max [[1]](#ref-1) 6. **10 November** (coming soon). 8t and 8i still coming soon on the TPU page, no price for any of the four [[7]](#ref-7) [[8]](#ref-8) I understand why. ## What I'd like to see A price on the page for TPU 8i, by the chip-hour, the way Ironwood has one, and a date. --- More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md) - Older: [What Sapolsky's first lecture means for LLMs and decision models](https://www.anchorterminal.com/blog/sapolsky-first-lecture-decision-models.md) - All posts: https://www.anchorterminal.com/blog/index.md Anchor Terminal grades the tools AI agents run on, with a source for every score. ## References Read on 10 November 2026. [1] Amin Vahdat, Google, Our newest TPUs, 8tx and 8i Max, built for the agentic era, 9 November 2026. Source for TPU 8tx and TPU 8i Max being the third and fourth eighth-generation systems, the first time Google introduced four TPU systems in a year, nearly 100 TPU customers including frontier labs, trading firms, retailers and universities, TPU 8tx's silicon, AMD EPYC hosts, hardware-level protection, target customers and workloads, and TPU 8i Max's two chips per package with double the compute, SRAM and HBM bandwidth of TPU 8i in the same rack footprint. [2] Data Center Knowledge, Google Adds TPU 8tx, 8i Max for Enterprise AI, 9 November 2026. Source for what it reported Mark Lohmeyer of Google Cloud said, that select customers will be able to deploy TPU 8tx in their own data centres and "We're just seeing tremendous demand for the TPU platform and systems". [3] Diwakar Gupta and Sabastian Mugazambi, Google Cloud, Inside the eighth-generation TPU, an architecture deep dive, 22 April 2026. Source for TPU 8i's 288 GB of HBM, 8,601 GB/s of HBM bandwidth, 384 MB of on-chip SRAM and pods of up to 1,152 chips. [4] Mark Lohmeyer and Bill Jia, Google Cloud, TorchTPU is now open source, run native PyTorch on TPUs, 20 October 2026. Source for TorchTPU being open source and co-developed with Meta's PyTorch team, running PyTorch workloads with minimal code changes, `device_map="tpu"` in Transformers v5, the vLLM and SGLang backends, and the quote from Meta's Jana van Greunen. [5] Ramanathan Venkatapathy and Rohit Jnagal, Google Cloud, Agent Compute Engine deep dive, 22 October 2026. Source for a hardware-isolated microVM per agent with no credentials inside it, idle agents suspended and resumed, "Agents spend most of their lives waiting", and a preview targeted for the coming months with an interest form. [6] Amin Vahdat, Google, Our eighth generation TPUs, two chips for the agentic era, 22 April 2026. Source for TPU 8t and TPU 8i being announced on 22 April, "Both chips will be generally available later this year", and the form to request more information. [7] Google Cloud, Tensor Processing Units (TPUs). [8] Google Cloud, Cloud TPU pricing. [9] Broadcom Inc.