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 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a8 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.17.0 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® 8 Elite Gen 5 Mobile 0.507 ms 0 - 36 MB NPU
GPUNet ONNX float Snapdragon® X2 Elite 0.477 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® X Elite 1.138 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.78 ms 0 - 59 MB NPU
GPUNet ONNX float Qualcomm® QCS8550 (Proxy) 1.045 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® QCS9075 1.349 ms 1 - 3 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.601 ms 0 - 30 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.351 ms 0 - 49 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.388 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.974 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.589 ms 0 - 61 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS6490 100.92 ms 22 - 32 MB CPU
GPUNet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.821 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS9075 0.977 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCM6690 49.458 ms 29 - 37 MB CPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.43 ms 0 - 42 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 38.092 ms 29 - 38 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.354 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.312 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.722 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.473 ms 0 - 61 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS6490 16.265 ms 1 - 14 MB CPU
GPUNet ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.616 ms 0 - 2 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS9075 0.718 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCM6690 10.304 ms 6 - 15 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.393 ms 0 - 39 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 7.748 ms 7 - 16 MB CPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.569 ms 1 - 37 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.651 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.437 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.922 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8275 (Proxy) 4.701 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.29 ms 1 - 2 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.757 ms 1 - 36 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS9075 1.574 ms 1 - 3 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.412 ms 0 - 61 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.701 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.299 ms 1 - 34 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.713 ms 0 - 36 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.44 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.569 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.235 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.762 ms 0 - 58 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS6490 3.226 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.462 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.062 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.295 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS9075 1.226 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCM6690 6.537 ms 0 - 159 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 1.435 ms 0 - 60 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.462 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.715 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.524 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.274 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.288 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.363 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.73 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.458 ms 0 - 55 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS6490 2.001 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.407 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.612 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.814 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS9075 0.701 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCM6690 3.53 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.844 ms 0 - 58 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.407 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.121 ms 0 - 36 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.346 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.796 ms 0 - 38 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.566 ms 0 - 67 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.899 ms 0 - 94 MB NPU
GPUNet TFLITE float Qualcomm® QCS8275 (Proxy) 4.632 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® QCS8550 (Proxy) 1.279 ms 0 - 2 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.747 ms 0 - 65 MB NPU
GPUNet TFLITE float Qualcomm® QCS9075 1.58 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 (Proxy) 2.402 ms 0 - 94 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.632 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.26 ms 0 - 61 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.704 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.233 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.343 ms 0 - 54 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS6490 1.639 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.112 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.424 ms 0 - 79 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.641 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS9075 0.529 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCM6690 3.047 ms 0 - 38 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.686 ms 0 - 56 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.112 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.93 ms 0 - 35 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.273 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.615 ms 0 - 37 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