A Piece of Stardust Trying to Make a Difference💫
Software Engineer  |•|  Astrophysics Enthusiast

github

Naman Gupta  • Peerlist

<h3>Experience the power of large language models directly on your Android device with QuantaLLM. This innovative application enables you to run sophisticated LLMs entirely offline, ensuring your data remains private and secure. Leveraging the efficiency of llama.cpp and accelerated by the Hexagon Neural Processing Unit (NPU), QuantaLLM delivers fast and responsive inference on ARM64 architecture. Enjoy the benefits of advanced AI capabilities without the need for an internet connection or reliance on cloud services. QuantaLLM is designed for developers and users seeking on-device AI solutions for enhanced privacy and performance.</h3><ul><li>On-Device LLM Inference: Run large language models locally on your Android phone.</li><li>100% Offline Operation: No internet connection required for inference.</li><li>Full Privacy: Your data stays on your device.</li><li>Hexagon NPU Acceleration: Optimized performance for compatible hardware.</li><li>Powered by llama.cpp: Utilizes a highly efficient LLM inference engine.</li><li>ARM64 Compatibility: Designed for modern Android devices.</li></ul>

Naman Gupta

A Piece of Stardust Trying to Make a Difference💫 Software Engineer |•| Astrophysics Enthusiast