Gemini Robotics On-Device brings AI to local robotic devices
Google just shipped a robotics model that runs locally. No cloud calls. No latency.

Why it matters
Google DeepMind is extending Gemini beyond text/vision into embodied AI with on-device inference—signaling a shift toward edge deployment of multimodal models and raising the stakes in the robotics AI race against OpenAI and Tesla.
The key facts
5 to knowGemini Robotics On-Device model announced
On-device inference capability (no cloud dependency)
General-purpose dexterity and fast task adaptation claimed
Multimodal robotics model release
Published June 24, 2025
Go to the source
Google DeepMind Blogdeepmind.google
Publisher excerpt: We’re introducing an efficient, on-device robotics model with general-purpose dexterity and fast task adaptation.