Hugging Face's logo

qualcomm
/
QuickSRNetLarge

Image-to-Image
PyTorch
android
Model card Files
xet
 Community

QuickSRNetLarge: Optimized for Qualcomm Devices

QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.

This is based on the implementation of QuickSRNetLarge 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 w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float 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 QuickSRNetLarge 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 QuickSRNetLarge on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.super_resolution

Model Stats:

  • Input resolution: 128x128
  • Model checkpoint: quicksrnet_large_3x_checkpoint
  • Model size (float): 1.67 MB
  • Model size (w8a8): 462 KB
  • Number of parameters: 436K

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
QuickSRNetLarge ONNX float Snapdragon® X2 Elite 1.206 ms 8 - 8 MB NPU
QuickSRNetLarge ONNX float Snapdragon® X Elite 1.997 ms 8 - 8 MB NPU
QuickSRNetLarge ONNX float Snapdragon® 8 Gen 3 Mobile 1.43 ms 0 - 39 MB NPU
QuickSRNetLarge ONNX float Snapdragon® 8 Gen 1 Mobile 3.512 ms 0 - 44 MB NPU
QuickSRNetLarge ONNX float Qualcomm® Dragonwing™ IQ-8275 3.838 ms 6 - 10 MB NPU
QuickSRNetLarge ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.907 ms 0 - 2 MB NPU
QuickSRNetLarge ONNX float Qualcomm® QCS8450 3.512 ms 0 - 44 MB NPU
QuickSRNetLarge ONNX float Qualcomm® Dragonwing™ IQ-9075 3.355 ms 7 - 10 MB NPU
QuickSRNetLarge ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.997 ms 8 - 8 MB NPU
QuickSRNetLarge ONNX float Qualcomm® Dragonwing™ Q-8750 1.199 ms 0 - 26 MB NPU
QuickSRNetLarge ONNX float Snapdragon® 8 Elite Mobile 1.199 ms 0 - 26 MB NPU
QuickSRNetLarge ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.943 ms 0 - 22 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® X2 Elite 0.356 ms 3 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® X Elite 0.782 ms 3 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.501 ms 0 - 37 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.07 ms 0 - 41 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 3.146 ms 0 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.874 ms 0 - 4 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.781 ms 0 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® QCS8450 1.07 ms 0 - 41 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.009 ms 0 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.782 ms 3 - 3 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 9.027 ms 2 - 144 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.105 ms 0 - 25 MB NPU
QuickSRNetLarge ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.386 ms 0 - 29 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® 8 Elite Mobile 0.386 ms 0 - 29 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.336 ms 0 - 26 MB NPU
QuickSRNetLarge ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.105 ms 0 - 25 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® X2 Elite 1.237 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® X Elite 2.018 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.286 ms 0 - 37 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.285 ms 0 - 42 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.631 ms 0 - 6 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 11.853 ms 0 - 22 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.82 ms 0 - 12 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® SA8775P 3.405 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® SA8650P 3.405 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® SA8255P 3.405 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® QCS8450 3.285 ms 0 - 42 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 3.27 ms 2 - 7 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 2.018 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.038 ms 0 - 23 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® SA7255P 11.853 ms 0 - 22 MB NPU
QuickSRNetLarge QNN_DLC float Qualcomm® SA8295P 3.928 ms 0 - 20 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® 8 Elite Mobile 1.038 ms 0 - 23 MB NPU
QuickSRNetLarge QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.861 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® X2 Elite 0.401 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® X Elite 0.759 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.437 ms 0 - 34 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.82 ms 0 - 39 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 3.062 ms 0 - 2 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.763 ms 0 - 3 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 2.119 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.661 ms 0 - 2 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® SA8775P 0.856 ms 0 - 25 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® SA8650P 0.856 ms 0 - 25 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® SA8255P 0.856 ms 0 - 25 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® QCS8450 0.82 ms 0 - 39 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.783 ms 0 - 2 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.759 ms 0 - 0 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 8.337 ms 0 - 135 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.909 ms 0 - 22 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.372 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® SA7255P 2.119 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Qualcomm® SA8295P 1.379 ms 0 - 21 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.372 ms 0 - 24 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.275 ms 0 - 25 MB NPU
QuickSRNetLarge QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.909 ms 0 - 22 MB NPU
QuickSRNetLarge TFLITE float Snapdragon® 8 Gen 3 Mobile 1.446 ms 0 - 38 MB NPU
QuickSRNetLarge TFLITE float Snapdragon® 8 Gen 1 Mobile 3.497 ms 0 - 45 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.832 ms 3 - 10 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® Dragonwing™ IQ-8275 12.178 ms 3 - 28 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.138 ms 0 - 4 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® SA8775P 3.811 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® SA8650P 3.811 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® SA8255P 3.811 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® QCS8450 3.497 ms 0 - 45 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® Dragonwing™ IQ-9075 3.64 ms 3 - 9 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® Dragonwing™ Q-8750 1.083 ms 0 - 25 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® SA7255P 12.178 ms 3 - 28 MB NPU
QuickSRNetLarge TFLITE float Qualcomm® SA8295P 4.207 ms 3 - 25 MB NPU
QuickSRNetLarge TFLITE float Snapdragon® 8 Elite Mobile 1.083 ms 0 - 25 MB NPU
QuickSRNetLarge TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.878 ms 0 - 28 MB NPU
QuickSRNetLarge TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.503 ms 0 - 35 MB NPU
QuickSRNetLarge TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.913 ms 0 - 40 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 2.95 ms 0 - 3 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.825 ms 0 - 4 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.196 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.789 ms 0 - 1 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® SA8775P 0.994 ms 0 - 27 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® SA8650P 0.994 ms 0 - 27 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® SA8255P 0.994 ms 0 - 27 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® QCS8450 0.913 ms 0 - 40 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.898 ms 0 - 3 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 8.559 ms 0 - 137 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.969 ms 0 - 24 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.406 ms 0 - 24 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® SA7255P 2.196 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE w8a8 Qualcomm® SA8295P 1.48 ms 0 - 24 MB NPU
QuickSRNetLarge TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.406 ms 0 - 24 MB NPU
QuickSRNetLarge TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.3 ms 0 - 26 MB NPU
QuickSRNetLarge TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.969 ms 0 - 24 MB NPU

License

  • The license for the original implementation of QuickSRNetLarge can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/QuickSRNetLarge