Google Research says it will reveal a new low-power Edge AI chip next week, co-designed with Synaptics and built using Google’s open-source AI hardware IP.

The chip is aimed at devices where power and thermal limits matter: smart glasses, watches, connected cameras, streaming hardware and industrial vision or voice systems. Google says the new design will improve efficiency and performance, but it has not yet published the chip’s full name, process node, TOPS rating, memory configuration or power envelope.

Introducing Coral NPU: A full-stack, open-source platform co-designed by Google Research and @GoogleDeepMind. It provides tools for developers to build the next generation of always-on AI on low-power edge devices. Learn how you can start building today: https://t.co/hNPPSwtmAg pic.twitter.com/FaYeVYu7hc

— Google Research (@GoogleResearch) October 15, 2025

The partnership already has shipping development hardware. The Synaptics Coralboard uses the Astra SL2619 processor and exposes Google Research’s Coral NPU through an open-source MLIR/IREE software stack. That gives developers a path to prototype on-device AI before moving toward production silicon.

The larger direction is clear even before the final specifications arrive: more inference is moving away from centralized servers and onto small devices that need local, responsive computing. BitcoinVersus.Tech has been tracking that shift through Renesas pushing AI into industrial edge hardware, our Top 7 AI Chips in 2026 and Infineon’s physical-AI hardware push.

BitcoinVersus.Tech Editor’s Note:
We volunteer daily to ensure the credibility of the information on this platform is Verifiably True. If you would like to support to help further secure the integrity of our research initiatives, please donate using the QR code provided

For best QR-code scanning results, please scan this donation code from a desktop or larger screen. Mobile screens may prevent camera recognition.