qualcomm/GenieX

On-device LLM Inference Powered by X-Bit Quantization

Open-source Llm for Apple silicon devices.

The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Demonstration of running a native LLM on Android device.

Production ready toolkit to run AI locally

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

One app for both cloud LLMs and on-device LLMs.

MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.