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.

75
/ 100
Verified

Provides Python SDK with integrated model export, quantization, and cloud-based profiling/inference against real Qualcomm hardware via AI Hub Workbench API. Supports multiple on-device runtimes (Qualcomm AI Engine Direct, LiteRT, ONNX) across CPU/GPU/NPU with precision options (FP32/FP16/INT8/INT16), enabling end-to-end model compilation pipelines with pre/post-processing in PyTorch and native deployment through linked sample applications.

940 stars. Actively maintained with 76 commits in the last 30 days.

No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

940

Forks

162

Language

Python

License

BSD-3-Clause

Last pushed

Mar 12, 2026

Commits (30d)

76

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/qualcomm/ai-hub-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.