software-mansion/react-native-executorch

React Native ExecuTorch is an on-device AI inference library for React Native, powered by ExecuTorch — Meta's on-device inference runtime. It lets you run machine learning models directly on the user's phone with zero network calls, full offline capability, and guaranteed privacy. No data ever leaves the device.

The library ships with a curated set of pre-exported models covering computer vision, language models, text-to-speech, transcription, and more — all available in our Hugging Face collection and ready to use out of the box. You can also bring your own .pte models and plug them into existing pipelines or build entirely custom ones from scratch.

To export your own PyTorch models to .pte, use ExecuTorch Export Recipes, our export harness with model recipes and agent skills.

To explore all on-device capabilities in an interactive showcase app, check out the React Native ExecuTorch Gallery.

Table of Contents

• Key Features
• Quickstart
  • 1. Installation
  • 2. Run the Model
• Documentation
• Powered by React Native ExecuTorch
• Created by Software Mansion

Key Features

• Native Hardware Acceleration: Optimized execution delegates across backends: XNNPACK (CPU), Core ML & MLX (Apple Silicon), and Vulkan (Android GPU).
• 100% Offline & Private: Zero cloud inference costs and zero network dependency after model download. No user data ever leaves the device.
• Two-Layer Architecture:
  • Ready-to-use Task Hooks (use<Task>): Out-of-the-box support for LLMs, computer vision, speech, and embeddings with automatic caching and lifecycle management.
  • Lower-level Runtime & Custom Orchestration: Build custom pipelines entirely in TypeScript using low-level tensor operations, fast native operators, schema validation, and worklet threading.
• Pre-Exported Model Catalog: Access verified models directly via the models registry and the Software Mansion Hugging Face Collections.

Quickstart

[!TIP] Using an AI coding agent? The consumer skill helps your agent choose ready-made models and task hooks, integrate a custom .pte, or build a custom TypeScript pipeline.

Install the consumer skill from the Software Mansion skills repository:

npx skills add software-mansion-labs/skills -s react-native-executorch

See AI Tools for model-selection guidance and an example prompt.

1. Installation

Install react-native-executorch alongside its required peer dependencies:

npm install react-native-executorch react-native-worklets react-native-blob-util
# or
yarn add react-native-executorch react-native-worklets react-native-blob-util
# or
pnpm add react-native-executorch react-native-worklets react-native-blob-util

[!IMPORTANT] React Native ExecuTorch requires:

• New Architecture enabled
• React Native 0.83+ or Expo SDK 55+ with Development Builds (Expo Go is not supported due to custom C++ native libraries)
• react-native-worklets 0.10 or newer (>=0.10.0 <0.14.0)
• iOS 17.0+ / Android 8.0+ (minSdkVersion >= 26)
• react-native-worklets/plugin as the last entry in your Babel plugins

Downloads of our pre-exported models send an anonymous download event; call setTelemetryEnabled(false) to opt out.

See the Getting Started Guide and Compatibility table for more details.

2. Run the Model

import { Button, View } from 'react-native';
import { models, useLLMChatSession } from 'react-native-executorch';

export function App() {
  const session = useLLMChatSession(models.llm.LFM2_5_1_2B.DEFAULT);

  const handleGenerate = async () => {
    if (!session.isReady || !session.sendMessage) return;

    const turn = await session.sendMessage(
      'Explain on-device AI in one sentence.',
      (token) => console.log(token)
    );

    console.log('Result messages:', turn.messages);
  };

  return (
    <View style={{ flex: 1, justifyContent: 'center', alignItems: 'center' }}>
      <Button
        title={session.isReady ? 'Generate' : `Loading (${session.downloadProgress.toFixed(0)}%)`}
        onPress={handleGenerate}
        disabled={!session.isReady}
      />
    </View>
  );
}

Documentation

Building with an AI coding agent? See AI Tools for model-selection guidance and an example prompt. Choose a pre-exported model with a task hook, or bring your own .pte and build a custom TypeScript pipeline.

Full documentation, guides, architecture deep dives, and API references are available at: docs.swmansion.com/react-native-executorch

• Getting Started Guide
• Downloading & Caching Models
• Task Extensions & Pipelines
• Core Primitives & Custom Pipelines
• Exporting Custom .pte Models

Powered by React Native ExecuTorch

React Native ExecuTorch powers Private Mind, a privacy-first mobile AI application available on App Store and Google Play.

It also powers these libraries:

• React Native RAG: private, on-device retrieval-augmented generation for your own documents.
• React Native OCR: on-device document OCR with page layout, tables, dewarping and vertical text.

Created by Software Mansion

Since 2012, Software Mansion has been building mobile and web apps, contributing to open-source software, and dealing with all kinds of React Native challenges. We are Core React Native Contributors. We can help you build your next AI product – Hire us.