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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
QuickSRNetLarge	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.946 ms	0 - 23 MB	NPU
QuickSRNetLarge	ONNX	float	Snapdragon® X2 Elite	1.217 ms	6 - 6 MB	NPU
QuickSRNetLarge	ONNX	float	Snapdragon® X Elite	2.208 ms	8 - 8 MB	NPU
QuickSRNetLarge	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.503 ms	0 - 39 MB	NPU
QuickSRNetLarge	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.98 ms	0 - 51 MB	NPU
QuickSRNetLarge	ONNX	float	Qualcomm® QCS9075	3.518 ms	7 - 10 MB	NPU
QuickSRNetLarge	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.249 ms	0 - 20 MB	NPU
QuickSRNetLarge	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.343 ms	0 - 27 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Snapdragon® X2 Elite	0.381 ms	3 - 3 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Snapdragon® X Elite	0.891 ms	3 - 3 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.494 ms	0 - 35 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.76 ms	0 - 2 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Qualcomm® QCS9075	0.966 ms	0 - 3 MB	CPU
QuickSRNetLarge	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.387 ms	0 - 23 MB	CPU
QuickSRNetLarge	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.82 ms	0 - 26 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Snapdragon® X2 Elite	1.218 ms	0 - 0 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Snapdragon® X Elite	2.01 ms	0 - 0 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.293 ms	0 - 37 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	11.864 ms	0 - 23 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.812 ms	0 - 8 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® SA8775P	3.414 ms	0 - 24 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® QCS9075	3.374 ms	0 - 5 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.268 ms	0 - 39 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® SA7255P	11.864 ms	0 - 23 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Qualcomm® SA8295P	3.965 ms	0 - 21 MB	NPU
QuickSRNetLarge	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.053 ms	0 - 26 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.247 ms	0 - 24 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.38 ms	0 - 0 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® X Elite	0.72 ms	0 - 0 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.4 ms	0 - 32 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCS6490	2.767 ms	0 - 2 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.939 ms	0 - 23 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.587 ms	0 - 1 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® SA8775P	0.789 ms	0 - 23 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCS9075	0.83 ms	0 - 2 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCM6690	8.346 ms	0 - 134 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.846 ms	0 - 32 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® SA7255P	1.939 ms	0 - 23 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Qualcomm® SA8295P	1.346 ms	0 - 20 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.33 ms	0 - 21 MB	NPU
QuickSRNetLarge	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.884 ms	0 - 21 MB	NPU
QuickSRNetLarge	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.852 ms	0 - 28 MB	NPU
QuickSRNetLarge	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.455 ms	0 - 40 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.32 ms	3 - 28 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.129 ms	0 - 1 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® SA8775P	3.778 ms	0 - 26 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® QCS9075	3.706 ms	3 - 9 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.507 ms	0 - 40 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® SA7255P	12.32 ms	3 - 28 MB	NPU
QuickSRNetLarge	TFLITE	float	Qualcomm® SA8295P	4.206 ms	0 - 21 MB	NPU
QuickSRNetLarge	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.083 ms	0 - 25 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.29 ms	0 - 25 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.484 ms	0 - 34 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCS6490	2.832 ms	0 - 3 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.17 ms	0 - 25 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.779 ms	0 - 1 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® SA8775P	1.039 ms	0 - 26 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCS9075	0.966 ms	0 - 3 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCM6690	8.479 ms	0 - 136 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.043 ms	0 - 35 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® SA7255P	2.17 ms	0 - 25 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Qualcomm® SA8295P	1.449 ms	0 - 22 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.371 ms	0 - 27 MB	NPU
QuickSRNetLarge	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.977 ms	0 - 23 MB	NPU

License

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

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/QuickSRNetLarge

QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms

Paper • 2303.04336 • Published Mar 8, 2023