# mybigday/llama.rn

React Native binding of llama.cpp

Repository: https://github.com/mybigday/llama.rn
Canonical: https://ross.abutalabs.com/products/llamarn
Language: C++
License: MIT
License Family: permissive
Topics: llama, llama-cpp, llm, react-native, android, ios
Last push: 2026-08-24T04:09:52+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 80
- inputs: {"age_days": 1127, "days_push": 9, "days_rel": 29, "gap_med": 6.0, "n_releases_24m": 59}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1026, forks 114 (observed 2026-08-28T04:03:16.688973+00:00)

## What it is
A React Native binding of llama.cpp that enables on-device LLM inference on iOS and Android. It supports GPU/NPU acceleration (Metal, Hexagon NPU), multimodal models, experimental on-device text-to-speech, parallel decoding, tool calling, and grammar-constrained sampling.

## Use cases
- run llama.cpp models locally in a react native app
- on-device llm inference on ios and android
- chat with a local llm offline on mobile
- add tool calling to a mobile llm app
- generate structured json output from a local model
- run speech or vision models on-device in react native
- mobile text-to-speech with voice cloning

## When to choose
- you build a React Native app and want private, offline LLM inference on-device
- you need Metal (iOS) or NPU/OpenCL (Android) acceleration for local models
- you want multimodal, TTS, or grammar-constrained generation in a mobile app

## When to avoid
- your app is not React Native - use llama.cpp bindings for your platform instead
- you need server-side or cloud LLM inference rather than on-device
- you must support React Native's Old Architecture (only v0.9.x branch does)

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, tts, speech-recognition, sdk
- domain: large-language-models, mobile-development, artificial-intelligence
- platform: cpp
- tags: llama-cpp, react-native, on-device-inference, gpu-acceleration, metal, npu, multimodal, tool-calling, grammar-sampling, voice-cloning, audio, android, ios, mobile

## Member repositories
- mybigday/llama.rn (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.688973+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 2026-08-30T07:07:59.170243+00:00, confidence not recorded.
  - readme: https://github.com/mybigday/llama.rn (fetched 2026-08-28T04:03:16.688973+00:00, sha a22ebad95c52)
- Data as of 2026-08-30T08:39:29.467469+00:00.