ChatterUI
An open-source Android LLM chat app that runs GGUF models on-device through llama.cpp or connects to Ollama, OpenAI and Claude. Licensed under AGPL-3.0.
ChatterUI is an Android chat app for people who want to run a local LLM on their phone or use the same interface with a remote model. It supports assistant conversations and character chats, with controls for how chats are structured and how models generate replies. It's open source under AGPL-3.0.
Local Mode runs GGUF models on the device through llama.cpp. The model must fit in your phone's memory, and inference happens on the phone rather than through a remote API. ChatterUI can use model files already in device storage or keep its own copy. Android is the available platform; iOS isn't available.
Remote Mode connects the mobile app to backends such as Ollama, koboldcpp and text-generation-webui, including those you host yourself. It also supports cloud services such as OpenAI, Claude and Cohere, alongside Open Router, Mancer and AI Horde. In this mode, the selected backend processes chat requests. Generic text and chat completion support, plus custom API templates, extend the app beyond its named connections.
For character conversations, ChatterUI supports Character Card v2 and keeps multiple chats per character. You can adjust generation settings and the instruction format rather than rely on a fixed chat setup. It also works with the phone's text-to-speech engine to read responses aloud.
