AI on Chrome
Welcome to the next era of the web with AI. See how AI can make it easier for developers to build powerful experiences on the web.
Gemini Nano in Chrome
Reimagine what's possible with Gemini Nano in Chrome.
Built-in AI
We're bringing Gemini Nano, the most efficient model of the Gemini ecosystem, to Chrome.
Why use on-device AI?
On-device AI brings powerful models to users, while protecting data privacy and improving latency.
Exploratory APIs
Review what's currently available for Gemini Nano in Chrome.
Start prototyping built-in APIs
Get an early preview of experimental Web APIs for on-device AI with Gemini Nano, our most efficient, on-device LLM.
Build with AI
Evaluate product reviews
Use server-side generative AI to evaluate reviews. Inference occurs on a server.
Help users share useful feedback
Explore on-device AI solutions to help users write insightful reviews.
On-device translation with AI
Discover the experimental Translate API to empower global customer support.
Cache AI models
Help your applications launch faster by caching the the model on-device.
AI and Gemini Nano news
Developer productivity
Console insights in DevTools
Use the Console to view and debug the results of on-device AI.
Write better prompts
The better your prompt, the more likely you'll get the results you need.
Web AI at I/O
We're adding Gemini Nano to Chrome, so developers can add generative AI features client-side to their websites and web apps, without servers.
Practical on-device AI for web developers
Built-in AI is delivers powerful models to users, while protecting sensitive data and improving latency. Look at real-world use cases and determine when built-in AI is right for you.
WebAssembly and WebGPU enhancements for faster Web AI
Learn how WebAssembly and WebGPU enhancements improve machine learning performance on the web.
New models, tools, and APIs for your next web app
Google's web AI libraries and models just reached 1 billion downloads. Learn what's new with the state of web AI at Google and discover generative AI models you can run client-side.
WebGPU
Support your AI efforts with WebGPU, a web graphics API that offers access to more advanced GPU features.
What's New in WebGPU
Disover the latest updates to WebGPU in Chrome.
Overview
Discover WebGPU in Chrome and get first-class support for general computations on the GPU.
Access the GPU
Learn how to access the GPU with WebGPU.
Web AI model testing in Google Colab
Learn how to test client-side, browser-based AI models in true browser environments.
Troubleshooting tips and fixes
Learn why WebGPU may be inoperable or not working as expected in Chrome, and how to fix it..
API reference
Find the API reference on MDN.
WebAssembly
Enable high-performance applications on web pages with Chrome
WebAssembly optimizations for AI inference
Learn about improvements to WebAssembly for tasks commonly used in AI inference.
TensorFlow.js Wasm backend
Learn about the TensorFlow.js Wasm backend WASM backend and how it uses the XNNPACK library for optimized implementation of neural network operators.
ONNX Runtime Web for WebAssembly
Learn how to deploy the ONNX Runtime Web in a production environment and which WebAssembly binary file(s) to include in the application.
Build with AI
What is AI?
Understand the basics and definitions of the various emerging technologies, often referred to as AI.
Ethics and AI
As web practitioners, it's critical that we build new technology thoughtfully and responsibly.
Upgrade your site search
Discover techniques to get contextual results from generative AI, at-scale.