mrousavy/react-native-fast-tflite

Health v2 · maintenance only

Adoption not part of the score

1240 stars · 92 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A high-performance TensorFlow Lite library for React Native built on Nitro Modules, using the low-level C/C++ TFLite core API with zero-copy ArrayBuffers. It supports GPU-accelerated delegates (CoreML/Metal/OpenGL), runtime model swapping, and easy VisionCamera integration.

Use cases

• run tensorflow lite models on-device in react native
• object detection from camera frames in a mobile app
• facial recognition in react native
• load and swap tflite models at runtime without rebuilding
• gpu-accelerated ml inference on ios and android
• integrate ml models with visioncamera

When to choose

• you need fast on-device TensorFlow Lite inference in a React Native app
• you want GPU delegates like CoreML, Metal, or OpenGL for acceleration
• you need to hot-swap .tflite models at runtime or load them from URLs
• you use VisionCamera and want frame-by-frame ML processing

When to avoid

• your app is not built with React Native
• you need training or full TensorFlow rather than lightweight inference
• you want a high-level API that interprets tensor outputs for you
• you target platforms outside iOS and Android

Facets

library · maturity active

machine-learning llm-inference image-processing computer-vision machine-learning mobile-development computer-vision cross-platform react-native tensorflow-lite tflite on-device-inference gpu-acceleration vision-camera nitro-modules zero-copy android ios mobile

Member repositories

For agents

markdown · JSON · MCP: product_card(name="margelo/react-native-fast-tflite")