What it does
The app runs quantized GGUF models on your Android phone with an embedded llama.cpp engine, or routes requests to cloud providers such as OpenAI, Claude, NVIDIA NIM, Hugging Face, OpenRouter and Gemini. It exposes standard OpenAI-compatible endpoints on your local network, so IDEs and tools that accept a custom base URL can use your phone as their model endpoint.
Who makes it
Ollama Local AI is developed by FreeRouter Team, an independent developer team. The developer website listed on Google Play is shannsingh.com. For questions, feedback or bug reports, email contact@shannsingh.com.
Independent from Ollama
Ollama Local AI is not affiliated with, sponsored by or endorsed by Ollama, OpenAI, Anthropic or any other provider it can connect to. It can use a self-hosted Ollama server as one of several providers. For the differences between the two, read Ollama Local AI vs Ollama.
App facts
| Developer | FreeRouter Team |
|---|---|
| Package name | com.llmproxy |
| Platform | Android 8.0 and newer |
| iPhone | Coming soon, not released yet |
| Price | Free to install, with optional in-app purchases |
| Google Play rating | 4.2 from 324 ratings (October 2026) |
| Google Play downloads | 10K+ (October 2026) |
| API endpoints | /v1/chat/completions, /v1/models, /health |
| Privacy | No data collected, per the Google Play data safety section. See the privacy summary. |
About the guides
The guides on this site describe features listed on the app's Google Play page and standard OpenAI-compatible API behavior. Each guide shows the date it was last updated. If a step does not match the version of the app you have, please email us so we can correct it.
