Gemini Nano is the most efficient model in Google's Gemini family, designed to run directly on phones and other devices instead of in the cloud.
In plain words
Gemini Nano runs on the device itself rather than on remote servers, so it can work without a connection and your data does not have to leave the phone. On Android it runs inside a system service called AICore, and app developers reach it through Google's ML Kit tools for things like summarising text or answering a custom prompt.
A quick example
Imagine a notes app that turns a long voice-memo transcript into a short bullet list, even while the phone is in airplane mode, because the model runs on the handset.
Where you'll meet it
- Android apps using ML Kit's on-device AI features.
- Features that need privacy or work offline.
Related
Sources
- DocsGemini Nano, Android Developers · read 29 Oct 2026
- DocsIntroducing Gemini: our largest and most capable AI model, Google · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Oct 2026. Spotted an error? Report it.