Gemini Nano

Our most efficient model for on-device tasks

1.0 Nano is optimized for providing quick responses, on-device — with or without a data network.

Nano size, mega utility

We're focused on making Nano the most powerful on-device model available. Later this year, Pixel and Android users will be the first to experience its new multimodal capabilities.

Image understanding
Richer and clearer descriptions of images and what’s in them.
Speech transcription
Understands what you’re saying so it’s possible to talk rather than type.
Text summarization
Distil messages, emails, and documents into concise, readable summaries.

Demo

Powerful, efficient understanding

Nano transforms the on-device experience, enabling seamless interactions with low latency and privacy by design.

Pixel Screenshots

Pixel Screenshots saves info you want to remember later - like events, places and more. It uses Gemini Nano with Multimodality and Tensor G4 to find what you need, right when you need it. [1]

Call Notes

On Pixel, Call Notes provides a completely private summary and transcript of a conversation. It's easy to activate, notifies everyone on the call, and runs on-device so it's completely private, thanks to Gemini Nano. [2]

Pixel Recorder

The Pixel Recorder application uses Gemini Nano and AICore to power an on-device summarization feature.

Gboard

Gboard leverages Gemini Nano with AICore to provide accurate smart reply capabilities on-device.

TalkBack

The TalkBack accessibility feature will use Nano’s multimodal capabilities to provide clear descriptions of images on Android phones.

Custom silicon, optimized for AI

Tensor G4 in the Pixel 9 phones was designed with Google DeepMind and is optimized to run our most advanced AI models. It's the first processor to run Gemini Nano with Multimodality - helping your phone understand text, images and audio.

Protected and private

Android is the first mobile operating system with a large, on-device multimodal AI model — your data never leaves your phone for some of the most sensitive use cases.

AI-powered tasks, built-in

With built-in AI, your browser provides and manages foundation and expert models.

AI-supported content creation

Such as writing assistance, proofreading, grammar correction, and rephrasing.

AI-enhanced content consumption

Including summarization, translation, answering questions about some content, categorization, and characterizing.

Research

Technical reports

May 2024

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

December 2023

Gemini 1.0: A family of highly capable multimodal models

For developers

Build with Gemini

Integrate Gemini models into your applications with Google AI Studio and Google Cloud Vertex AI.

Build

Google AI Studio

An easy way to develop model prompts and build quickly with the Gemini API.