mybigday/llama.rn

Health v2 · maintenance only

Adoption not part of the score

1026 stars · 114 forks observed · 2026-08-28

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

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

library · maturity active

llm-inference tts speech-recognition sdk large-language-models mobile-development artificial-intelligence cpp llama-cpp react-native on-device-inference gpu-acceleration metal npu multimodal tool-calling grammar-sampling voice-cloning audio android ios mobile

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mybigday/llama.rn")