qualcomm/ai-hub-models

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.

What it solves

It provides a curated collection of state-of-the-art machine learning models specifically optimized for deployment on Qualcomm hardware, reducing the friction of compiling, quantizing, and profiling models for on-device execution.

How it works

Users can browse and download optimized models via a CLI or Python API. Through integration with the Qualcomm AI Hub Workbench, the project automates the pipeline of compiling a model for a specific target runtime (like TFLite or ONNX) and precision (like INT8 or FP16), profiling its performance on real cloud-hosted devices, and running inference to verify accuracy against PyTorch outputs.

Who it’s for

Developers building AI applications for Qualcomm-powered devices, including Android smartphones (Samsung Galaxy, Xiaomi), Windows laptops (Snapdragon X Elite), and automotive or IoT platforms.

Highlights

  • Comprehensive Model Zoo: Includes a wide variety of models for image classification, image editing, super-resolution, and semantic segmentation.
  • Hardware-Specific Optimization: Supports deployment across CPU, GPU, and NPU (including Hexagon DSP and HTP).
  • Automated Workflow: Streamlines the process from model export and quantization to on-device profiling and inference.
  • End-to-End Demos: Provides CLI-based demos that handle preprocessing, inference, and post-processing for immediate testing.

Related

  • Project
    qualcomm/ai-hub-apps

    A collection of sample apps and tutorials for deploying and optimizing machine learning models on Qualcomm Snapdragon devices across Android, Windows, and Ubuntu.

  • Project
    google-ai-edge/litert-samples

    A collection of official and community samples, model recipes, and deployment tools for LiteRT and LiteRT-LM to enable high-performance on-device ML execution.

  • 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
    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.

  • Project
    onnx/models

    A curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, enabling cross-framework compatibility and deployment.