Back to News

Google unveils TPU 8tx with AMD CPUs and TPU 8i Max dual-chip for long-context tasks, launching 2027

#google#tpu#amd#ai-chips

Google announced two specialized TPUs: the TPU 8tx, designed to pair with AMD CPUs, and the TPU 8i Max, a dual-chip package aimed at long-context window tasks. Both are slated to launch in 2027, expanding Google's AI chip lineup as it seeks to build on its rapid growth in the sector.

Coverage timeline

  1. Techmeme
    Google unveils two specialized TPUs, the TPU 8tx, to be paired with AMD CPUs, and TPU 8i Max, a dual-chip package for long-context window tasks, launching 2027 (Dina Bass/Bloomberg)

    Dina Bass / Bloomberg : Google unveils two specialized TPUs, the TPU 8tx, to be paired with AMD CPUs, and TPU 8i Max, a dual-chip package for long-context window tasks, launching 2027 — Alphabet Inc.'s Google is rolling out a broader array of artificial intelligence chips, aiming to capitalize on its rapid ascent …

Related stories

  • Google launches TorchTPU, vLLM adds TPU backend

    Google announced TorchTPU, an open-source version of PyTorch that lets AI applications run on TPUs and Google Cloud via simple configuration changes without rewriting code. Concurrently, vLLM introduced vllm-torchtpu, a new backend for Google Cloud TPUs built on TorchTPU, featuring Pallas kernels, multi-host parallelism, KV cache offloading, and disaggregated serving. These moves, following Amazon's similar tool, challenge Nvidia's dominance in AI development.

    3 reports · 3 sources

  • OpenAI Plans to Buy Google TPUs, Seeks Engineer for Model Optimization

    OpenAI plans to purchase Google's TPUs, according to a person familiar with the matter, marking a potential shift for a major Nvidia customer. A job listing reveals OpenAI is seeking an engineer to lead optimization of its models on TPUs, boosting a competitor to Nvidia.

    1 reports · 1 sources

  • Google's Suncatcher satellite runs Gemma 4 on TPU in orbit, sends first AI response

    Google announced that its Project Suncatcher prototype data center satellite, launched on October 1, is online and has completed its first on-orbit inference run. The satellite's Tensor Processing Units (TPUs) powered a Gemma 4 model that generated a haiku about being in space, marking the first complete AI response from a data-center-grade TPU in orbit. Google CEO Sundar Pichai called it a 'Hello World' moment for the project, which aims to eventually place AI data centers in space.

    4 reports · 4 sources

  • Google DeepMind unveils Gemini 4 Carbon, tops AI benchmark

    Google DeepMind announced Gemini 4 Carbon, its next frontier model, claiming state-of-the-art performance in cybersecurity and long-horizon tasks. The model scored 59 on the Artificial Analysis Intelligence Index v5.0, ranking first ahead of Claude Opus 5.5 (58) and GPT-6 Astra (57). It is initially available only to select cybersecurity defense companies through the Fairwind program, with pricing at $2 per million input tokens and $10 per million output tokens, rising to $4 and $20 later.

    8 reports · 6 sources1013 points · 801 comments

News updates every hour. Subscribe in your RSS reader to get new stories automatically.

Subscribe