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 0.472 ms 2 - 2 MB NPU
GPUNet ONNX float Snapdragon® X Elite 0.985 ms 25 - 25 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.764 ms 0 - 63 MB NPU
GPUNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.721 ms 1 - 63 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.504 ms 1 - 4 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.014 ms 0 - 142 MB NPU
GPUNet ONNX float Qualcomm® QCS8450 1.721 ms 1 - 63 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.544 ms 1 - 3 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.985 ms 25 - 25 MB NPU
GPUNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.601 ms 0 - 30 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Mobile 0.601 ms 0 - 30 MB NPU
GPUNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.517 ms 0 - 36 MB NPU
GPUNet ONNX w8a16 Snapdragon® X2 Elite 0.385 ms 1 - 1 MB NPU
GPUNet ONNX w8a16 Snapdragon® X Elite 0.833 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.59 ms 0 - 70 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.124 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 3.454 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.876 ms 0 - 4 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.82 ms 0 - 17 MB NPU
GPUNet ONNX w8a16 Qualcomm® QCS8450 1.124 ms 0 - 69 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.149 ms 0 - 3 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.833 ms 12 - 12 MB NPU
GPUNet ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 5.758 ms 0 - 170 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 - 50 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Mobile 0.435 ms 0 - 50 MB NPU
GPUNet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.367 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 0.333 ms 1 - 1 MB NPU
GPUNet ONNX w8a8 Snapdragon® X Elite 0.6 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 0.88 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 2.11 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.711 ms 0 - 4 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.62 ms 0 - 42 MB NPU
GPUNet ONNX w8a8 Qualcomm® QCS8450 0.88 ms 0 - 66 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.742 ms 0 - 3 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.6 ms 12 - 12 MB NPU
GPUNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 3.279 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 0.391 ms 0 - 42 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.391 ms 0 - 42 MB NPU
GPUNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.356 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 0.644 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® X Elite 1.392 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.917 ms 0 - 56 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.394 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.63 ms 1 - 4 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.671 ms 1 - 31 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.274 ms 1 - 2 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8775P 1.702 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8650P 1.702 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8255P 1.702 ms 1 - 33 MB NPU
GPUNet QNN_DLC float Qualcomm® QCS8450 2.394 ms 0 - 63 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.573 ms 1 - 3 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.392 ms 1 - 1 MB NPU
GPUNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.702 ms 0 - 30 MB NPU
GPUNet QNN_DLC float Qualcomm® SA7255P 4.671 ms 1 - 31 MB NPU
GPUNet QNN_DLC float Qualcomm® SA8295P 2.293 ms 0 - 31 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.702 ms 0 - 30 MB NPU
GPUNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.572 ms 1 - 36 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X2 Elite 0.575 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® X Elite 1.226 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.772 ms 0 - 59 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.456 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 4.073 ms 2 - 4 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.097 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 2.483 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.069 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8775P 1.287 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8650P 1.287 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8255P 1.287 ms 0 - 45 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® QCS8450 1.456 ms 0 - 65 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.152 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.226 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 6.584 ms 0 - 168 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.296 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.519 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA7255P 2.483 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a16 Qualcomm® SA8295P 1.67 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.519 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.432 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.296 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 0.702 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.455 ms 0 - 57 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.846 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 2.243 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.665 ms 0 - 3 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.431 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.615 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8775P 0.8 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8650P 0.8 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8255P 0.8 ms 0 - 42 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® QCS8450 0.846 ms 0 - 62 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.697 ms 0 - 2 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.702 ms 0 - 0 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 3.548 ms 0 - 43 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.791 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.339 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA7255P 1.431 ms 0 - 40 MB NPU
GPUNet QNN_DLC w8a8 Qualcomm® SA8295P 1.12 ms 0 - 38 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.339 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.297 ms 0 - 44 MB NPU
GPUNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.791 ms 0 - 40 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.913 ms 0 - 79 MB NPU
GPUNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.405 ms 0 - 82 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.631 ms 0 - 28 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.712 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.264 ms 0 - 56 MB NPU
GPUNet TFLITE float Qualcomm® SA8775P 1.748 ms 0 - 46 MB NPU
GPUNet TFLITE float Qualcomm® SA8650P 1.748 ms 0 - 46 MB NPU
GPUNet TFLITE float Qualcomm® SA8255P 1.748 ms 0 - 46 MB NPU
GPUNet TFLITE float Qualcomm® QCS8450 2.405 ms 0 - 82 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.68 ms 0 - 27 MB NPU
GPUNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.698 ms 0 - 43 MB NPU
GPUNet TFLITE float Qualcomm® SA7255P 4.712 ms 0 - 44 MB NPU
GPUNet TFLITE float Qualcomm® SA8295P 2.284 ms 0 - 44 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Mobile 0.698 ms 0 - 43 MB NPU
GPUNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.566 ms 0 - 45 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.344 ms 0 - 56 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.68 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.811 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.517 ms 0 - 15 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.112 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.429 ms 0 - 6 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8775P 0.638 ms 0 - 42 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8650P 0.638 ms 0 - 42 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8255P 0.638 ms 0 - 42 MB NPU
GPUNet TFLITE w8a8 Qualcomm® QCS8450 0.68 ms 0 - 62 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.53 ms 0 - 14 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 2.991 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.617 ms 0 - 39 MB NPU
GPUNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.275 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA7255P 1.112 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Qualcomm® SA8295P 0.912 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.275 ms 0 - 37 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.238 ms 0 - 40 MB NPU
GPUNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.617 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