News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
Edge TPU

Edge TPU

AI accelerator chip for edge devices by Google Coral

The Edge TPU is an application-specific integrated circuit designed by Google for artificial intelligence tasks at the network edge. It enables local processing of machine learning models on small devices with low power consumption.

Share on WhatsApp

  • Designed by Google for local AI processing
  • Uses open-source RISC-V based architecture
  • Supports PyTorch, JAX and LiteRT models
  • Enables ultra-low power AI at the edge

What it is

The Edge TPU is a specialised hardware component created by Google to run artificial intelligence workloads locally on devices. It forms part of the Coral platform, which aims to provide efficient AI capabilities without relying on cloud servers. The chip is designed to handle machine learning models directly on embedded systems, allowing for faster response times and improved data privacy.

Inside the chip

The architecture relies on an open-source design based on the RISC-V instruction set. This approach allows developers to integrate high-performance AI functions into custom silicon solutions. The system uses a standards-based MLIR compiler toolchain to convert models from frameworks like PyTorch, JAX, or LiteRT into instructions the hardware can execute. This structure supports a unified experience for engineers deploying intelligent features across various device types.

Where it went

This processor is intended for next-generation edge devices that require local intelligence. It powers applications where data must be processed immediately, such as in industrial sensors or smart home gadgets. The platform provides reference designs to help manufacturers build products that leverage ultra-low power AI. It is suitable for environments where energy efficiency and offline operation are critical requirements for the end user.

Questions people ask about Edge TPU

What is the Edge TPU used for?

It is an AI accelerator chip that runs machine learning models locally on small devices. This allows for intelligent processing at the network edge without needing a cloud connection.

Which company makes the Edge TPU?

Google designs the Edge TPU as part of its Coral platform. The company provides the hardware architecture and software tools for developers to use in their own products.

What software frameworks does it support?

The platform supports models from PyTorch, JAX, and LiteRT. Developers use MLIR compiler toolchains to translate these models so they can run efficiently on the hardware.

Good reading and sources

    Where this page comes from

    There is no English Wikipedia article on Edge TPU yet, so the facts on this page come from the sources listed above: coral.ai/technology/, geeky-gadgets.com/coral-ai-dual-edge-accelerator/. Some are the subject's own pages, so its claims about itself are reported as its claims. EveryChip wrote the text in its own words, with AI assistance, and compares it with the sources to make sure no passage is copied.

    It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

    The weekly digest

    Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.