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.
- 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
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.