IPADS-SAI/Mobiinfer-Android

Demonstration of running a native LLM on Android device.

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

On-device AI assistant for Android built with Kotlin, featuring local LLM inference, offline AI capabilities, and edge AI experimentation.

The agent that grows with you

1-Click LLM Server on Your Phone — no Termux needed! 无需Termux，一键让你的手机变成LLM服务器！

Mobile App Open