Qualcomm AI Hub Models
Project record
Maintained by Qualcomm Technologies, Inc.23
A Python package and GitHub repository of machine learning models prepared for deployment on Qualcomm devices. It provides export scripts that compile, quantize where applicable, profile, and run models through Qualcomm AI Hub Workbench, end-to-end demos for most models, and sample application code. Many of the packaged models come from other developers, such as YOLO, Llama, Mistral, Phi, and Qwen variants.1
- Repository: GitHub repository (external site: github.com)
- Website: Qualcomm AI Hub (external site: aihub.qualcomm.com)
- Documentation: PyPI package (qai-hub-models) (external site: pypi.org)
- License: License (BSD 3-Clause) (external site: github.com)
- Release notes: Release v0.63.0 (external site: github.com)
Availability and license
Overall availability
The code is public. Compiling, quantizing, profiling, and running models on hosted devices requires a Qualcomm ID and an AI Hub Workbench API token.1
Availability is separate from permission: read the license before using or redistributing.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Developed in the public qualcomm/ai-hub-models GitHub repository.1 |
| DocumentationIs user documentation published? | Public | The README covers setup, model export, end-to-end demos, and supported runtimes, chipsets, and devices; each model has its own README.15 |
| InstallationAre installation instructions or packages publicly available? | Public | Published on PyPI as qai-hub-models and installable with pip.13 |
| Supported platformsAre supported operating systems or hardware documented? | Public | The README lists Qualcomm AI Engine Direct (Android, Linux, Windows), LiteRT (Android, Linux), and ONNX Runtime (Android, Linux, Windows) as on-device runtimes; PyPI lists Python 3.10 to 3.13.13 |
| Release statusAre versioned releases published? | Public | Versioned releases are published on GitHub and PyPI, including v0.63.0 on September 23, 2026.43 |
What it is useful for
Preparing models for on-device runtimes (Qualcomm AI Engine Direct, LiteRT, and ONNX Runtime) on Snapdragon and other Qualcomm platforms, and checking on-device output against PyTorch output on cloud-hosted devices.1
Run and use notes
- The README documents a command-line interface (qai-hub-models) for browsing and downloading deployable model assets. End-to-end demos can run locally in PyTorch or on cloud-hosted Qualcomm devices through AI Hub Workbench.1
Organization context
Provenance and derivatives
U.S. eligibility
Eligible · basis: U.S.-governed project
The repository is published under the qualcomm GitHub organization, its license names Qualcomm Technologies, Inc. as copyright holder, and the PyPI package lists Qualcomm Technologies, Inc. as author. Qualcomm Technologies, Inc. is a subsidiary of QUALCOMM Incorporated, a Delaware corporation with principal executive offices in San Diego, California.2378
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.