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:

  • 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® X2 Elite 0.473 ms 2 - 2 MB NPU
GPUNet ONNX float Snapdragon® X Elite 0.987 ms 24 - 24 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.762 ms 0 - 63 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.711 ms 1 - 64 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.498 ms 1 - 4 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.013 ms 0 - 29 MB NPU
GPUNet ONNX float Qualcomm® QCS8450 1.711 ms 1 - 64 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.387 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.987 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 0.518 ms 0 - 36 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.386 ms 1 - 1 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.842 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.588 ms 0 - 68 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.142 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 3.441 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.878 ms 0 - 4 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.817 ms 0 - 16 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS8450 1.142 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.931 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.842 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 5.761 ms 0 - 172 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.064 ms 0 - 47 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 0.372 ms 0 - 50 MB NPU
GPUNet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.064 ms 0 - 47 MB NPU
GPUNet ONNX w8a8 Snapdragon® X2 Elite 0.308 ms 1 - 1 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.602 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.466 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.878 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 2.011 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.695 ms 0 - 4 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.613 ms 0 - 91 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS8450 0.878 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.767 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.602 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 3.221 ms 0 - 48 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.751 ms 0 - 44 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.392 ms 0 - 42 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.392 ms 0 - 42 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.35 ms 0 - 49 MB NPU
GPUNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.751 ms 0 - 44 MB NPU
GPUNet QNN_DLC float Snapdragon® X2 Elite 0.632 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.397 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.913 ms 0 - 61 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.408 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.624 ms 1 - 4 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.671 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.269 ms 1 - 2 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.72 ms 1 - 34 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8650P 1.72 ms 1 - 34 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8255P 1.72 ms 1 - 34 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 2.408 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.571 ms 1 - 3 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.397 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.703 ms 1 - 31 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.671 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.284 ms 0 - 32 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.703 ms 1 - 31 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.573 ms 1 - 34 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.575 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.225 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.771 ms 0 - 60 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.44 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 4.087 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.09 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 2.504 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.071 ms 1 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.274 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8650P 1.274 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8255P 1.274 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 1.44 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.151 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.225 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 6.592 ms 0 - 168 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.292 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.527 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.504 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.654 ms 0 - 41 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.527 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.44 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.292 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.345 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® X Elite 0.715 ms 1 - 1 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.465 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 2.211 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.662 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.414 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.614 ms 0 - 14 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.81 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8650P 0.81 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8255P 0.81 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 0.692 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.715 ms 1 - 1 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 3.469 ms 0 - 44 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 0.337 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.414 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.097 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.337 ms 0 - 39 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.291 ms 0 - 42 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 0.909 ms 0 - 78 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.397 ms 0 - 83 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.631 ms 0 - 28 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.711 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.263 ms 0 - 20 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.757 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8650P 1.757 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA8255P 1.757 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 2.397 ms 0 - 83 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.608 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.707 ms 0 - 47 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.711 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.272 ms 0 - 44 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Mobile 0.707 ms 0 - 47 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.558 ms 0 - 48 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.327 ms 0 - 55 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.661 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.776 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.515 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.111 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.429 ms 0 - 4 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.636 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8650P 0.636 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8255P 0.636 ms 0 - 43 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 0.661 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.536 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 3.02 ms 0 - 41 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.615 ms 0 - 38 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.272 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.111 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.906 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.272 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.24 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.615 ms 0 - 38 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