# mrousavy/react-native-fast-tflite

🧬 High-performance TensorFlow Lite library for React Native with GPU acceleration

Repository: https://github.com/mrousavy/react-native-fast-tflite
Canonical: https://ross.abutalabs.com/products/react-native-fast-tflite
Homepage: https://mrousavy.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, arraybuffer, camera, detection, facial-recognition, fast, ml, native, object-detection, react, react-native, tensorflow, tensorflow-lite, tflite, hacktoberfest
Last push: 2026-08-14T09:02:08+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 68, longevity 82
- inputs: {"age_days": 1156, "days_push": 19, "days_rel": 134, "gap_med": 49, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1222, forks 91 (observed 2026-08-28T04:04:02.466676+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, image-processing, computer-vision
- domain: machine-learning, mobile-development, computer-vision
- platform: cross-platform
- tags: react-native, tensorflow-lite, tflite, on-device-inference, gpu-acceleration, vision-camera, nitro-modules, zero-copy, android, ios, mobile

## Member repositories
- mrousavy/react-native-fast-tflite (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.466676+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:38.596417+00:00, confidence not recorded.
  - readme: https://github.com/mrousavy/react-native-fast-tflite (fetched 2026-08-28T04:04:02.466676+00:00, sha 2b56aea2d277)
  - homepage: https://mrousavy.com (fetched 2026-08-29T12:23:55.491243+00:00, sha cacb056158e6)
  - registry_npm: https://registry.npmjs.org/react-native-fast-tflite (fetched 2026-08-29T12:23:55.500309+00:00, sha f82b7fa15214)
- Data as of 2026-08-30T08:39:29.467469+00:00.