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 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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 0.477 ms 2 - 2 MB NPU
GPUNet ONNX float Snapdragon® X Elite 0.984 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.763 ms 0 - 61 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.715 ms 1 - 63 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.016 ms 0 - 62 MB NPU
GPUNet ONNX float Qualcomm® QCS8450 1.715 ms 1 - 63 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.422 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.984 ms 24 - 24 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.599 ms 0 - 32 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Mobile 0.599 ms 0 - 32 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.519 ms 0 - 32 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.385 ms 1 - 1 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.832 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.587 ms 0 - 70 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.115 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 3.4 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.815 ms 0 - 16 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS8450 1.115 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.934 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.832 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.435 ms 0 - 51 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Mobile 0.435 ms 0 - 51 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.367 ms 0 - 50 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.302 ms 1 - 1 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.598 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.467 ms 0 - 63 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.879 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 2.124 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.623 ms 0 - 37 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS8450 0.879 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.74 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.598 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.392 ms 0 - 43 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.392 ms 0 - 43 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.36 ms 0 - 46 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.657 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.38 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.919 ms 0 - 57 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.414 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8275 4.691 ms 1 - 32 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.274 ms 0 - 13 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.72 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8650P 1.72 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8255P 1.72 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 2.414 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.809 ms 3 - 5 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.38 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.704 ms 0 - 30 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.691 ms 1 - 32 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.261 ms 0 - 32 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.704 ms 0 - 30 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.571 ms 1 - 32 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.56 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.228 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.767 ms 0 - 60 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.43 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 4.069 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8275 2.475 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.068 ms 0 - 73 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.284 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8650P 1.284 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8255P 1.284 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 1.43 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.153 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.228 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 6.608 ms 0 - 165 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.293 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.525 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.475 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.644 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.525 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.44 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.293 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.34 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.699 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.461 ms 0 - 57 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.852 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 2.234 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8275 1.41 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.614 ms 0 - 69 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.806 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8650P 0.806 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8255P 0.806 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 0.852 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.696 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.699 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 3.556 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.788 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.341 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.41 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.096 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.341 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.295 ms 0 - 46 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.788 ms 0 - 40 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.911 ms 0 - 74 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.4 ms 0 - 81 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8275 4.714 ms 0 - 43 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.261 ms 0 - 13 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.748 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8650P 1.748 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8255P 1.748 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 2.4 ms 0 - 81 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.613 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.699 ms 0 - 43 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.714 ms 0 - 43 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.267 ms 0 - 44 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Mobile 0.699 ms 0 - 43 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.566 ms 0 - 47 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 0.685 ms 0 - 64 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.798 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8275 1.096 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.429 ms 0 - 16 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.694 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8650P 0.694 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8255P 0.694 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 0.685 ms 0 - 64 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.542 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 3.023 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.615 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.265 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.096 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.907 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.265 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.24 ms 0 - 41 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.615 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