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 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.515 ms 0 - 34 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.595 ms 0 - 33 MB NPU
GPUNet ONNX float Snapdragon® X2 Elite 0.465 ms 2 - 2 MB NPU
GPUNet ONNX float Snapdragon® X Elite 0.978 ms 25 - 25 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.746 ms 1 - 60 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.643 ms 1 - 66 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.501 ms 1 - 5 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.013 ms 0 - 29 MB NPU
GPUNet ONNX float Qualcomm® QCS8450 1.643 ms 1 - 66 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.388 ms 1 - 4 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.978 ms 25 - 25 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.595 ms 0 - 33 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.37 ms 0 - 52 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.436 ms 0 - 56 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.387 ms 1 - 1 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.864 ms 13 - 13 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.592 ms 0 - 70 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.047 ms 0 - 74 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 2.756 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.894 ms 0 - 4 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.838 ms 0 - 16 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS8450 1.047 ms 0 - 74 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.967 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.864 ms 13 - 13 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 5.782 ms 0 - 168 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.087 ms 0 - 52 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.436 ms 0 - 56 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.087 ms 0 - 52 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.358 ms 0 - 51 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.401 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.302 ms 1 - 1 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.594 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.466 ms 0 - 67 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.767 ms 0 - 70 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.738 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.702 ms 0 - 4 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.611 ms 0 - 14 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS8450 0.767 ms 0 - 70 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.724 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.594 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 3.247 ms 0 - 49 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.706 ms 0 - 49 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.401 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.706 ms 0 - 49 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.569 ms 1 - 36 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.706 ms 0 - 38 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.626 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.404 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.908 ms 0 - 60 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.248 ms 0 - 66 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.638 ms 1 - 4 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.28 ms 1 - 2 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.702 ms 1 - 39 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8650P 1.702 ms 1 - 39 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8255P 1.702 ms 1 - 39 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 2.248 ms 0 - 66 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.58 ms 1 - 3 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.404 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.706 ms 0 - 38 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.155 ms 0 - 35 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.457 ms 0 - 47 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.533 ms 0 - 51 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.596 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.234 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.762 ms 0 - 64 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.323 ms 0 - 70 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 3.366 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.093 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.083 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8650P 1.282 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8255P 1.282 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 1.323 ms 0 - 70 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.165 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.234 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 6.519 ms 0 - 160 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.311 ms 0 - 48 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.533 ms 0 - 51 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.463 ms 0 - 48 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.542 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.311 ms 0 - 48 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.296 ms 0 - 47 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.341 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.343 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.71 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.456 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.751 ms 0 - 68 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 2.033 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.666 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.598 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.776 ms 0 - 46 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8650P 0.776 ms 0 - 46 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8255P 0.776 ms 0 - 46 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 0.751 ms 0 - 68 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.684 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.71 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 3.561 ms 0 - 46 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.796 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.341 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.401 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 0.965 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.796 ms 0 - 45 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.56 ms 0 - 52 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.7 ms 0 - 51 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.894 ms 0 - 78 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.236 ms 0 - 85 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.644 ms 0 - 28 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.253 ms 0 - 125 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.694 ms 0 - 51 MB NPU
GPUNet TFLITE float Qualcomm® SA8650P 1.694 ms 0 - 51 MB NPU
GPUNet TFLITE float Qualcomm® SA8255P 1.694 ms 0 - 51 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 2.236 ms 0 - 85 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.557 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.7 ms 0 - 51 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.682 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.144 ms 0 - 47 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.236 ms 0 - 44 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.273 ms 0 - 48 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.342 ms 0 - 60 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.561 ms 0 - 68 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.57 ms 0 - 16 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.505 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.412 ms 0 - 2 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 0.561 ms 0 - 68 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.519 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 3.012 ms 0 - 44 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.618 ms 0 - 44 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.273 ms 0 - 48 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.09 ms 0 - 44 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.762 ms 0 - 41 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.618 ms 0 - 44 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