Hugging Face's logo

qualcomm
/
GPUNet

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community

GPUNet: Optimized for Qualcomm Devices

GPUNet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of GPUNet found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit GPUNet on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for GPUNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 10.49M
  • Model size (float): 45.28MB
  • Model size (w8a8): 21.3MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
GPUNet ONNX float Snapdragon® X2 Elite 0.472 ms 2 - 2 MB NPU
GPUNet ONNX float Snapdragon® X Elite 0.974 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.764 ms 1 - 61 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.703 ms 1 - 63 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.004 ms 0 - 29 MB NPU
GPUNet ONNX float Qualcomm® QCS8450 1.703 ms 1 - 63 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.519 ms 0 - 33 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Mobile 0.601 ms 0 - 30 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.386 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.601 ms 0 - 30 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.974 ms 24 - 24 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.382 ms 1 - 1 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.84 ms 13 - 13 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.575 ms 0 - 65 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.153 ms 0 - 68 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 3.368 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.818 ms 0 - 16 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS8450 1.153 ms 0 - 68 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Mobile 0.434 ms 0 - 47 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.145 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.059 ms 0 - 47 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.37 ms 0 - 51 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 5.769 ms 0 - 175 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.059 ms 0 - 47 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.434 ms 0 - 47 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.84 ms 13 - 13 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.303 ms 1 - 1 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.602 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.471 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.876 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 2.138 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.613 ms 0 - 14 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS8450 0.876 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.392 ms 0 - 46 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.751 ms 0 - 44 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.74 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.354 ms 0 - 49 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 3.293 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.751 ms 0 - 44 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.392 ms 0 - 46 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.602 ms 12 - 12 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.7 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.393 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.91 ms 0 - 61 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.394 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8275 4.692 ms 1 - 32 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.27 ms 1 - 17 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.697 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8650P 1.697 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8255P 1.697 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 2.394 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.57 ms 1 - 37 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.713 ms 0 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.593 ms 3 - 5 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.692 ms 1 - 32 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.282 ms 0 - 31 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.713 ms 0 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.393 ms 1 - 1 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.56 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.219 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.76 ms 0 - 60 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.424 ms 0 - 64 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 4.112 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8275 2.495 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.068 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.276 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8650P 1.276 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8255P 1.276 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 1.424 ms 0 - 64 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.528 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.148 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.495 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.667 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.286 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.441 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 6.553 ms 0 - 167 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.286 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.528 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.219 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.343 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.718 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.447 ms 0 - 57 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.853 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 2.256 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8275 1.406 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.608 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.803 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8650P 0.803 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8255P 0.803 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 0.853 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.341 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.789 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.693 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.406 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.104 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.292 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 3.558 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.789 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.341 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.718 ms 0 - 0 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.898 ms 0 - 73 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.395 ms 0 - 82 MB NPU
GPUNet TFLITE float Qualcomm® QCS8275 4.724 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.271 ms 0 - 2 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.76 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8650P 1.76 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8255P 1.76 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 2.395 ms 0 - 82 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.563 ms 0 - 47 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Mobile 0.696 ms 0 - 42 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.882 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.724 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.264 ms 0 - 43 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.696 ms 0 - 42 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.343 ms 0 - 55 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.686 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.846 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8275 1.113 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.426 ms 0 - 2 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.639 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8650P 0.639 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8255P 0.639 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 0.686 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.268 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.613 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.521 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.113 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.897 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.239 ms 0 - 42 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 3.017 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.613 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.268 ms 0 - 39 MB NPU

License

  • The license for the original implementation of GPUNet can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/GPUNet