Vali-98/ChatterUI

A frontend for running models on mobile or connecting to your preferred API providers.

What it solves

ChatterUI provides a native mobile interface for interacting with Large Language Models (LLMs), allowing users to run models locally on their devices or connect to various external APIs without needing a desktop environment.

How it works

The app operates in two primary modes:

  • Local Mode: Uses llama.cpp via a custom React Native adapter to run GGUF model files directly on the mobile device's hardware.
  • Remote Mode: Connects to commercial APIs (like OpenAI, Claude, and Cohere) or open-source backends (such as Ollama, Koboldcpp, and text-generation-webui).

Who it’s for

Mobile users who want a dedicated, customizable chat interface for LLMs, specifically those who prefer on-device privacy or the flexibility to switch between different API providers.

Highlights

  • Hybrid Execution: Supports both on-device inferencing and remote API connections.
  • Character-Based Chat: Supports the Character Card v2 specification for creating and interacting with specific personas.
  • Customization: Allows users to modify sampler fields and instruct formatting.
  • Accessibility: Integrates with the device's native text-to-speech (TTS) engine.

Related

  • Dispatch
    LLM Inference on Edge: Running Local LLMs via React Native

    Hugging Face provides a comprehensive guide to building a privacy-focused mobile application using React Native and llama.rn to run quantized GGUF models locally on Android and iOS.

  • Project
    addyosmani/chatty

    A private, in-browser AI chat interface that uses WebGPU to run LLMs locally on your hardware for offline use and data privacy.

  • Project
    OpenBMB/MiniCPM-V-Apps

    OpenBMB’s MiniCPM‑V‑Apps repo provides three on‑device demo apps (iOS, Android, HarmonyOS) that run MiniCPM‑V multimodal LLMs locally via a fork of llama.cpp. It includes build scripts, model‑download instructions, and hardware requirements for models ranging from 1 B to a 35 B MoE that streams experts from SSD.

  • Project
    netdur/llama_cpp_dart

    A Dart FFI binding for llama.cpp that enables running LLMs, vision, and audio models locally within Flutter apps on iOS and Android.

  • Project
    undreamai/LLMUnity

    A Unity engine integration for Large Language Models that enables the creation of intelligent, local AI characters with RAG support.