Quic Devface Ai

Leo Migdal

-Nov 18, 2025, 4:45 AM

Welcome to our repository! Here, we provide a collection of AI plugins specifically designed for Windows on Snapdragon applications. These plugins are developed using the Qualcomm AI Engine Direct SDK (QNN). Our AI plugins offer the following key features: Check out Contribution Guidelines for more details. We welcome contributions of all kinds!

You can ask questions and get support on: This project is licensed under the BSD-3-Clause License. For the full license text, please refer to the LICENSE file in this repository. This document provides an introduction to the qai_hub_models repository, a Python package containing 140+ state-of-the-art machine learning models optimized for deployment on Qualcomm devices. This overview covers the package structure, model catalog organization, and the high-level workflow for compiling and deploying models to target hardware. Scope: This page introduces the overall system architecture and core concepts.

For detailed information about specific subsystems: Sources: README.md1-356 qai_hub_models/_version.py1-7 The qai_hub_models package (version 0.41.0) is a PyPI-installable library that provides pre-optimized implementations of machine learning models designed to run efficiently on Qualcomm hardware. Each model includes: The package supports three primary on-device runtimes: Discover and explore top open-source AI tools and projects—updated daily.

The Qualcomm® AI Hub Apps repository provides a collection of open-source sample applications and tutorials for deploying machine learning models on Qualcomm® devices. It targets developers looking to optimize on-device AI performance, offering recipes for various ML tasks and end-to-end workflow guidance. The apps leverage Qualcomm® AI Hub Models and support multiple runtimes including TensorFlow Lite, ONNX, and the Genie SDK for generative AI. Deployment targets are Android (API v30+) and Windows 11, with compute options spanning CPU, GPU, and NPU (Hexagon HTP). NPU acceleration requires specific Snapdragon chipsets and FP16 or INT8 precision. To get started, locate the desired OS and app within the repository's folders.

Each app's README contains specific build and installation instructions. Supported deployment targets include Android 11 (API v30+) and Windows 11. NPU acceleration is optimized for Snapdragon chipsets (e.g., 8 Elite, 8 Gen 3/2/1, 888/888+). This repository is maintained by Qualcomm. Specific community channels or roadmaps are not detailed in the provided README. Run your models now on the Snapdragon® 8 Elite Gen 5 on AI Hub.

Explore models from Mistral on Qualcomm AI Hub Learn more about PLaMo 1B by Preferred Networks Integrate Granite‑3B‑Code‑Instruct into your applications Try out Llama3.2, the open‑source AI model you can fine‑tune, distill and deploy anywhere Qualcomm has released ' Qualcomm AI Hub ', a collection of machine learning models optimized for local operation on smartphones, and ' Snapdragon X80 5G Modem-RF System ', a 5G communication system with a... We announced ' FastConnect 7900 ', a Wi-Fi 7 and Bluetooth communication chip that realizes communication with low power and low latency, at the mobile related trade show '

Qualcomm also publishes operational examples of machine learning models distributed on Qualcomm AI Hub. In the movie below, you can see how the machine learning model ' LLaVA ', which can recognize images and answer questions, operates on a smartphone. World's first large multimodal model (LMM) on an Android phone - YouTube The demo movie below shows how to generate images using Stable Diffusion and LoRA on a smartphone. Low rank adaptation (LoRA) on an Android phone - YouTube The machine learning models distributed by Qualcomm AI Hub can operate not only on smartphones but also on PCs equipped with ' Snapdragon X... In the movie below, you can see how the ``large-scale language model that recognizes audio'' operates locally on a Windows PC. World's first large multimodal model (LMM) with audio reasoning on a Windows PC - YouTube Machine learning models optimized for Snapdragon can be downloaded not only from Qualcomm AI Hub but also from the...

GitHub - quic/ai-hub-models: Qualcomm® AI Hub Models is a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices. https://github.com/quic/ai-hub-models Qualcomm (Qualcomm) https://huggingface.co/qualcomm ◆Snapdragon X80 5G Modem-RF System The Snapdragon X80 5G Modem-RF System is a 5G communication system with a built-in 'AI tensor accelerator' for AI processing, which reduces power consumption and improves delay processing performance. In addition, the Snapdragon X80 5G Modem-RF System uses AI to manage millimeter wave beamforming, and it is also possible to use a high-speed positioning system using AI. Details of the Snapdragon X80 5G Modem-RF System can be found at the link below.

Snapdragon X80 5G Modem-RF System | Qualcomm https://www.qualcomm.com/products/technology/modems/snapdragon-x80-5g-modem-rf-system The Qualcomm® AI Hub Apps are a collection of sample apps and tutorials to help deploy machine learning models on Qualcomm® devices. Each app is designed to work with one or more models from Qualcomm® AI Hub Models. Weight and activation type required for NPU Acceleration: NOTE: These apps will run without NPU acceleration on non-Snapdragon® chipsets. Search for your desired OS & app in this folder, or in the app directory at the bottom of this file.

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for deployment on Qualcomm® devices. See supported: On-Device Runtimes, Hardware Targets & Precision, Chipsets, Devices Some models (e.g. YOLOv7) require additional dependencies. View the model README (at qai_hub_models/models/model_id) for installation instructions. Many features of AI Hub Models (such as model compilation, on-device profiling, etc.) require access to Qualcomm® AI Hub:

All models in our directory can be compiled and profiled on a hosted Qualcomm® device:

Quic Devface Ai

People Also Search

Welcome To Our Repository! Here, We Provide A Collection Of

You Can Ask Questions And Get Support On: This Project

For Detailed Information About Specific Subsystems: Sources: README.md1-356 Qai_hub_models/_version.py1-7 The

The Qualcomm® AI Hub Apps Repository Provides A Collection Of

Each App's README Contains Specific Build And Installation Instructions. Supported