XLSR: Optimized for Qualcomm Devices

XLSR is designed for lightweight real-time upscaling of images.

This is based on the implementation of XLSR 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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit XLSR 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 XLSR on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.super_resolution

Model Stats:

Model checkpoint: xlsr_3x_checkpoint
Input resolution: 128x128
Number of parameters: 28.0K
Model size (float): 115 KB
Model size (w8a8): 45.6 KB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
XLSR	ONNX	float	Snapdragon® X2 Elite	0.438 ms	6 - 6 MB	NPU
XLSR	ONNX	float	Snapdragon® X Elite	1.059 ms	8 - 8 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.675 ms	0 - 28 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.936 ms	0 - 67 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS9075	1.243 ms	6 - 9 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.51 ms	0 - 19 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.426 ms	0 - 22 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X2 Elite	0.248 ms	1 - 1 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X Elite	0.651 ms	3 - 3 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.368 ms	0 - 29 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS6490	11.878 ms	19 - 22 MB	CPU
XLSR	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.549 ms	0 - 2 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS9075	0.692 ms	0 - 3 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCM6690	8.416 ms	17 - 24 MB	CPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.261 ms	0 - 24 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	6.094 ms	18 - 25 MB	CPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.244 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X2 Elite	0.414 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X Elite	0.885 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.475 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.166 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.771 ms	0 - 68 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8775P	1.145 ms	0 - 22 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS9075	1.134 ms	0 - 5 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.05 ms	0 - 30 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA7255P	2.166 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8295P	1.354 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.362 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.317 ms	0 - 24 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.263 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X Elite	0.483 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.249 ms	0 - 27 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS6490	1.421 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.906 ms	0 - 20 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.372 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8775P	0.578 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS9075	0.526 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCM6690	1.682 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.53 ms	0 - 28 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA7255P	0.906 ms	0 - 20 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8295P	0.788 ms	0 - 17 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.197 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.397 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.162 ms	0 - 21 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.459 ms	0 - 29 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.798 ms	3 - 23 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.229 ms	0 - 67 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8775P	2.673 ms	0 - 21 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS9075	2.614 ms	3 - 8 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.564 ms	0 - 30 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA7255P	4.798 ms	3 - 23 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8295P	3.364 ms	0 - 17 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.001 ms	0 - 20 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.827 ms	0 - 22 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.237 ms	0 - 29 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS6490	1.122 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.896 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.388 ms	0 - 60 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8775P	0.617 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS9075	0.586 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCM6690	1.604 ms	0 - 19 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.532 ms	0 - 30 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA7255P	0.896 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8295P	0.779 ms	0 - 17 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.213 ms	0 - 24 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.399 ms	0 - 19 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.163 ms	0 - 22 MB	NPU

License

The license for the original implementation of XLSR 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/XLSR

Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices

Paper • 2105.10288 • Published May 21, 2021