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® X Elite 1.133 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.789 ms 0 - 57 MB NPU
GPUNet ONNX float Qualcomm® QCS8550 (Proxy) 1.044 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® QCS9075 1.351 ms 1 - 3 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.607 ms 0 - 36 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.504 ms 0 - 35 MB NPU
GPUNet ONNX float Snapdragon® X2 Elite 0.471 ms 24 - 24 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.993 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.595 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS6490 97.34 ms 22 - 33 MB CPU
GPUNet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.829 ms 0 - 17 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS9075 0.972 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCM6690 49.645 ms 30 - 38 MB CPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.433 ms 0 - 42 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 38.175 ms 35 - 43 MB CPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.362 ms 0 - 49 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.387 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.723 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.476 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS6490 16.573 ms 3 - 13 MB CPU
GPUNet ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.613 ms 0 - 14 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS9075 0.72 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCM6690 10.085 ms 6 - 15 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.397 ms 0 - 47 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 7.743 ms 7 - 15 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.357 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.315 ms 12 - 12 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.431 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.923 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8275 (Proxy) 4.674 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.292 ms 1 - 2 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 7.417 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS9075 1.576 ms 1 - 3 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.405 ms 0 - 65 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.674 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.294 ms 1 - 34 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.706 ms 1 - 37 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.57 ms 1 - 37 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.668 ms 1 - 1 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.266 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.758 ms 0 - 61 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS6490 3.22 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.463 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.061 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.276 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS9075 1.232 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCM6690 6.578 ms 0 - 160 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 1.425 ms 0 - 60 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.463 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.75 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.528 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.281 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.443 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.564 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 0.462 ms 0 - 56 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS6490 2.012 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.423 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.612 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.83 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS9075 0.695 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCM6690 3.516 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.867 ms 0 - 58 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.423 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.103 ms 0 - 36 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.339 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.799 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.292 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.359 ms 0 - 0 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.9 ms 0 - 97 MB NPU
GPUNet TFLITE float Qualcomm® QCS8275 (Proxy) 4.645 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® QCS8550 (Proxy) 1.279 ms 0 - 2 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 7.284 ms 0 - 63 MB NPU
GPUNet TFLITE float Qualcomm® QCS9075 1.578 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 (Proxy) 2.414 ms 0 - 94 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.645 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.28 ms 0 - 62 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.702 ms 0 - 63 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.566 ms 0 - 67 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.338 ms 0 - 54 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS6490 1.606 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.116 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.419 ms 0 - 2 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.633 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS9075 0.524 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCM6690 3.043 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.677 ms 0 - 56 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.116 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.895 ms 0 - 35 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.263 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.616 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.235 ms 0 - 43 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