QuickSRNetSmall: Optimized for Qualcomm Devices

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

This is based on the implementation of QuickSRNetSmall 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 2.45	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 QuickSRNetSmall 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 QuickSRNetSmall on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.super_resolution

Model Stats:

Model checkpoint: quicksrnet_small_3x_checkpoint
Input resolution: 128x128
Number of parameters: 33.3K
Model size (float): 133 KB
Model size (w8a8): 41.7 KB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
QuickSRNetSmall	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.401 ms	0 - 21 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® 8 Elite Mobile	0.474 ms	0 - 22 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® X2 Elite	0.376 ms	6 - 6 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® X Elite	1.026 ms	9 - 9 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® X Elite	1.026 ms	9 - 9 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.6 ms	0 - 26 MB	NPU
QuickSRNetSmall	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.894 ms	0 - 26 MB	NPU
QuickSRNetSmall	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.474 ms	0 - 22 MB	NPU
QuickSRNetSmall	ONNX	float	Qualcomm® QCS9075	1.165 ms	6 - 9 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.215 ms	0 - 21 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.251 ms	0 - 22 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® X2 Elite	0.203 ms	3 - 3 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® X Elite	0.608 ms	3 - 3 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® X Elite	0.608 ms	3 - 3 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.333 ms	0 - 27 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.502 ms	0 - 9 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Qualcomm® QCS9075	0.666 ms	0 - 3 MB	NPU
QuickSRNetSmall	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.251 ms	0 - 22 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.317 ms	0 - 24 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.35 ms	0 - 24 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® X2 Elite	0.424 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® X Elite	0.855 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® X Elite	0.855 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.452 ms	0 - 27 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.735 ms	0 - 12 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® SA8775P	1.084 ms	0 - 22 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® SA8775P	1.084 ms	0 - 22 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® SA8775P	1.084 ms	0 - 22 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® SA7255P	1.879 ms	0 - 20 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.023 ms	0 - 29 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® SA8295P	1.369 ms	0 - 18 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.35 ms	0 - 24 MB	NPU
QuickSRNetSmall	QNN_DLC	float	Qualcomm® QCS9075	1.117 ms	2 - 7 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.155 ms	0 - 23 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.194 ms	0 - 20 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.247 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® X Elite	0.479 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® X Elite	0.479 ms	0 - 0 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.222 ms	0 - 27 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® QCS6490	1.288 ms	0 - 2 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.351 ms	0 - 13 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® SA8775P	0.545 ms	0 - 21 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® SA8775P	0.545 ms	0 - 21 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® SA8775P	0.545 ms	0 - 21 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® QCS9075	0.502 ms	0 - 2 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.194 ms	0 - 20 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.423 ms	0 - 28 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® SA7255P	0.837 ms	0 - 19 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.372 ms	0 - 18 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® QCM6690	1.285 ms	0 - 16 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Qualcomm® SA8295P	0.732 ms	0 - 17 MB	NPU
QuickSRNetSmall	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.372 ms	0 - 18 MB	NPU
QuickSRNetSmall	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.396 ms	0 - 24 MB	NPU
QuickSRNetSmall	TFLITE	float	Snapdragon® 8 Elite Mobile	0.454 ms	0 - 20 MB	NPU
QuickSRNetSmall	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.613 ms	0 - 28 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.989 ms	0 - 2 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® SA8775P	1.39 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® SA8775P	1.39 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® SA8775P	1.39 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® SA7255P	2.38 ms	0 - 21 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.311 ms	0 - 29 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® SA8295P	1.651 ms	0 - 17 MB	NPU
QuickSRNetSmall	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.454 ms	0 - 20 MB	NPU
QuickSRNetSmall	TFLITE	float	Qualcomm® QCS9075	1.282 ms	1 - 6 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.174 ms	0 - 23 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.228 ms	0 - 19 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.255 ms	0 - 28 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® QCS6490	1.059 ms	0 - 2 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.406 ms	0 - 2 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® SA8775P	0.605 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® SA8775P	0.605 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® SA8775P	0.605 ms	0 - 22 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® QCS9075	0.534 ms	0 - 3 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.228 ms	0 - 19 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.47 ms	0 - 28 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® SA7255P	0.898 ms	0 - 18 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.427 ms	0 - 17 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® QCM6690	1.503 ms	0 - 16 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Qualcomm® SA8295P	0.832 ms	0 - 17 MB	NPU
QuickSRNetSmall	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.427 ms	0 - 17 MB	NPU

License

The license for the original implementation of QuickSRNetSmall 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/QuickSRNetSmall

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

Paper • 2303.04336 • Published Mar 8, 2023