local-ai

llama.rn

Name: llama.rn
Author: mybigday

React Native binding of llama.cpp

1,010 stars110 forksC++Updated 7/28/2026100% free · open source

What it does

Llama.rn allows you to integrate the LLaMA AI model into your React Native applications, enabling local AI capabilities on mobile devices.

Install / run

git clone https://github.com/mybigday/llama.rn.git

When to use it

•You're building a mobile app that requires AI-powered features like text analysis or generation without relying on remote servers.
•Your React Native project needs to support offline AI functionality, reducing dependence on internet connectivity.
•You want to leverage the LLaMA model's capabilities in a React Native environment for tasks such as language translation or summarization.

Quick start

1Run `npm install` in the cloned repository to set up the necessary dependencies.
2Open the `ExampleApp` folder and run `npx react-native run-ios` or `npx react-native run-android` to start the example application.
3Modify the `ExampleApp.js` file to integrate llama.rn functionality into your own React Native components.
4Use the `LlamaRN` module in your JavaScript code to interact with the LLaMA model, as shown in the example app's source code.
5Configure the model settings and parameters according to your specific use case, following the documentation and README guidelines.

Ready-to-paste prompt

const LlamaRN = require('./LlamaRN'); LlamaRN.predict('This is a test input');

Heads up: Ensure you have the necessary C++ build tools and environment setup to compile llama.cpp, as the React Native binding relies on the native module being built correctly.

Saves to your device