qualcomm/ai-hub-apps

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.

Qualcomm® AI Hub Apps – What It Is

Purpose – A curated set of sample applications and step‑by‑step tutorials that show how to run machine‑learning models on Qualcomm hardware (Snapdragon CPUs, GPUs and Hexagon NPUs). The apps demonstrate end‑to‑end inference pipelines for common vision, audio and language tasks and are built on the runtimes that Qualcomm supports.

Key features

  • Multiple runtimes – TensorFlow Lite, ONNX Runtime and Qualcomm’s own Genie SDK (for generative AI).
  • Cross‑platform – Ready‑made code for Android (Java/Kotlin), Windows (C++/Python/Go) and Ubuntu (Python).
  • Hardware acceleration – Instructions for using CPU, GPU and the Hexagon NPU (HTP) on Snapdragon chipsets, with details on required data types (FP16, INT8/INT16).
  • Task catalogue – Image classification, object detection, semantic segmentation, super‑resolution, speech‑to‑text (Whisper), stable diffusion, hand‑gesture recognition, pose estimation, audio classification, face recognition, 3D detection, LiDAR segmentation, and LLM chat via GenieX.
  • Tutorials – Guides for exporting and running large language models on‑device with the Genie SDK.

Typical workflow

  1. Pick a task and platform from the tables in the README.
  2. Follow the app‑specific README to build (e.g., Gradle for Android, CMake for Windows, pip for Ubuntu) and install the required runtime libraries.
  3. Load a compatible model from the Qualcomm AI Hub Model catalog.
  4. Run the app; the code will automatically select the best available compute unit (CPU/GPU/NPU) based on the device.

Who it’s for – Developers who want concrete, compile‑ready examples of on‑device inference on Snapdragon devices, or who need a reference implementation for integrating Qualcomm’s AI Engine Direct / Genie SDK into their own products.

License – BSD‑3 Clause, allowing free use and modification.

Quick reference table

Platform Language Runtime Example tasks
Android Java / Kotlin TensorFlow Lite, GenieX Image classification, object detection, segmentation, WhisperKit, GenieX chat
Windows C++ / Python / Go ONNX, GenieX Classification, detection, super‑resolution, Whisper, Stable Diffusion, SAM3
Ubuntu Python TensorFlow Lite Hand‑gesture, pose, audio, face, 3D detection, LiDAR segmentation

Bottom line – This repo is a genuine, practical resource for building AI‑enabled applications that run directly on Qualcomm Snapdragon hardware.

Related

  • Project
    qualcomm/ai-hub-models

    Qualcomm AI Hub Models is a Python package and CLI that provides a catalog of pre‑optimised machine‑learning models (vision, language, generative AI) ready for deployment on Snapdragon CPUs, GPUs, and NPUs. It handles quantisation, compilation, and performance profiling on real Qualcomm devices via the AI Hub Workbench, and includes sample apps and demos for both local PyTorch inference and on‑device accelerated runtimes.

  • Project
    google-ai-edge/litert-samples

    Google AI Edge LiteRT Samples is a genuine open‑source collection of on‑device machine‑learning demos, model‑conversion recipes, and automation tools for LiteRT (the successor to TensorFlow Lite) and LiteRT‑LM. It provides Android, iOS, and Web/WASM examples covering speech, vision, text‑to‑image, and multimodal apps, plus scripts to convert Hugging Face checkpoints into LiteRT‑compatible bundles. The repo is aimed at developers building high‑performance edge AI applications.

  • Project
    Arm-Examples/ML-examples

    A collection of machine learning examples and tutorials for deploying and optimizing AI models on Arm Ethos NPUs and Cortex-based platforms.

  • Project
    Liquid4All/cookbook

    A collection of tutorials, code examples, and deployment guides for building edge-native AI applications using Liquid Foundation Models and the LEAP SDK.

  • Project
    amd/RyzenAI-SW

    A suite of tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI-based PCs to maximize hardware acceleration.