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® X2 Elite 0.468 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® X Elite 1.118 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.786 ms 0 - 61 MB NPU
GPUNet ONNX float Qualcomm® QCS8550 (Proxy) 1.042 ms 1 - 2 MB NPU
GPUNet ONNX float Qualcomm® QCS9075 1.358 ms 1 - 3 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.609 ms 0 - 37 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.508 ms 0 - 36 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.393 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.999 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.58 ms 0 - 65 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS6490 97.936 ms 23 - 33 MB CPU
GPUNet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.825 ms 0 - 16 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS9075 0.971 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCM6690 49.794 ms 28 - 35 MB CPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.434 ms 0 - 45 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 38.154 ms 30 - 38 MB CPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.36 ms 0 - 49 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.309 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.729 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.472 ms 0 - 62 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS6490 16.511 ms 0 - 13 MB CPU
GPUNet ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.614 ms 0 - 2 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS9075 0.723 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCM6690 10.212 ms 6 - 14 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.392 ms 0 - 47 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 7.805 ms 6 - 15 MB CPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.362 ms 0 - 48 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.646 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.414 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.915 ms 0 - 62 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8275 (Proxy) 4.664 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.286 ms 1 - 136 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.756 ms 1 - 36 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS9075 1.595 ms 3 - 5 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.404 ms 0 - 65 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.664 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.305 ms 0 - 33 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.706 ms 0 - 33 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.572 ms 1 - 37 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.564 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.261 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.75 ms 0 - 58 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS6490 3.206 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.443 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.074 ms 0 - 83 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.29 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS9075 1.226 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCM6690 6.565 ms 0 - 159 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 1.415 ms 0 - 61 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.443 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.707 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.534 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.28 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.429 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.37 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.722 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.466 ms 0 - 56 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS6490 1.998 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.4 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.606 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.81 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS9075 0.703 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCM6690 3.523 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.848 ms 0 - 58 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.4 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.077 ms 0 - 36 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.332 ms 0 - 37 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.796 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.292 ms 0 - 44 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.905 ms 16 - 112 MB NPU
GPUNet TFLITE float Qualcomm® QCS8275 (Proxy) 4.638 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® QCS8550 (Proxy) 1.291 ms 0 - 151 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.751 ms 0 - 64 MB NPU
GPUNet TFLITE float Qualcomm® QCS9075 1.581 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 (Proxy) 2.403 ms 0 - 94 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.638 ms 0 - 62 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.291 ms 0 - 61 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.703 ms 0 - 62 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.564 ms 0 - 66 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.333 ms 0 - 54 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS6490 1.583 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.101 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.434 ms 0 - 2 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.641 ms 0 - 41 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS9075 0.528 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCM6690 3.044 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.674 ms 0 - 56 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.101 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.906 ms 0 - 35 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.263 ms 0 - 35 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 0.234 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