React Native ExecuTorch

React Native ExecuTorch is a declarative way to run AI models in React Native on device, powered by ExecuTorch 🚀.

ExecuTorch is a novel framework created by Meta that enables running AI models on devices such as mobile phones or microcontrollers. React Native ExecuTorch bridges the gap between React Native and native platform capabilities, allowing developers to run AI models locally on mobile devices with state-of-the-art performance, without requiring deep knowledge of native code or machine learning internals.

Table of contents:

Compatibility
Ready-made models 🤖
Documentation 📚
Quickstart - Running Llama 🦙
Minimal supported versions
Examples 📲
License
What's next?

Compatibility

React Native Executorch supports only the New React Native architecture.

If your app still runs on the old architecture, please consider upgrading to the New Architecture.

Ready-made models 🤖

To run any AI model in ExecuTorch, you need to export it to a .pte format. If you're interested in experimenting with your own models, we highly encourage you to check out the Python API. If you prefer focusing on developing your React Native app, we will cover several common use cases. For more details, please refer to the documentation.

Documentation 📚

Take a look at how our library can help build you your React Native AI features in our docs:
https://docs.swmansion.com/react-native-executorch

Quickstart - Running Llama 🦙

Get started with AI-powered text generation in 3 easy steps!

1️⃣ Installation

# Install the package
yarn add react-native-executorch
cd ios && pod install && cd ..

2️⃣ Setup & Initialization

Add this to your component file:

import {
  useLLM,
  LLAMA3_2_1B,
  LLAMA3_2_TOKENIZER,
  LLAMA3_2_TOKENIZER_CONFIG,
} from 'react-native-executorch';

function MyComponent() {
  // Initialize the model 🚀
  const llama = useLLM({
    modelSource: LLAMA3_2_1B,
    tokenizerSource: LLAMA3_2_TOKENIZER,
    tokenizerConfigSource: LLAMA3_2_TOKENIZER_CONFIG,
  });
  // ... rest of your component
}

3️⃣ Run the model!

const handleGenerate = async () => {
  const chat = [
    { role: 'system' content: 'You are a helpful assistant' }
    { role: 'user', content: 'What is the meaning of life?' }
  ];

  // Chat completion
  await llm.generate(chat);
  console.log('Llama says:', llm.response);
};

Minimal supported versions

The minimal supported version are:

iOS 17.0
Android 13

Examples 📲

We currently host a few example apps demonstrating use cases of our library:

apps/llm - chat application showcasing use of LLMs
apps/speech-to-text - Whisper and Moonshine models ready for transcription tasks
apps/computer-vision - computer vision related tasks
apps/text-embeddings - computing text representations for semantic search

If you would like to run it, navigate to it's project directory, for example apps/llm from the repository root and install dependencies with:

yarn

And then, if you want to run on Android:

yarn expo run:android

or iOS:

yarn expo run:ios

Warning ⚠️

Running LLMs requires a significant amount of RAM. If you are encountering unexpected app crashes, try to increase the amount of RAM allocated to the emulator.

License

This library is licensed under The MIT License.

What's next?

To learn about our upcoming plans and developments, please visit our discussion page.