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 1.24.3	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 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® 8 Elite Gen 5 Mobile	0.425 ms	0 - 22 MB	NPU
XLSR	ONNX	float	Snapdragon® X2 Elite	0.406 ms	6 - 6 MB	NPU
XLSR	ONNX	float	Snapdragon® X Elite	1.076 ms	9 - 9 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.648 ms	0 - 29 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.943 ms	0 - 59 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS9075	1.24 ms	6 - 9 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.506 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.242 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X2 Elite	0.25 ms	1 - 1 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X Elite	0.664 ms	3 - 3 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.35 ms	0 - 30 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS6490	12.183 ms	19 - 21 MB	CPU
XLSR	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.548 ms	0 - 27 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS9075	0.698 ms	0 - 3 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCM6690	8.475 ms	18 - 24 MB	CPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.264 ms	0 - 20 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	6.428 ms	17 - 24 MB	CPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.323 ms	0 - 24 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X2 Elite	0.444 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X Elite	0.882 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.472 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.152 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.775 ms	0 - 11 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8775P	1.156 ms	0 - 22 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS9075	1.109 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	2.152 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8295P	1.383 ms	0 - 17 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.365 ms	0 - 20 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.166 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.277 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X Elite	0.482 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.245 ms	0 - 28 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS6490	1.402 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.904 ms	0 - 20 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.393 ms	0 - 1 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8775P	0.582 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS9075	0.521 ms	2 - 4 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCM6690	1.667 ms	0 - 17 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.525 ms	0 - 28 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA7255P	0.904 ms	0 - 20 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8295P	0.782 ms	0 - 17 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.187 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.408 ms	0 - 18 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.825 ms	0 - 22 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.462 ms	0 - 29 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.826 ms	3 - 24 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.228 ms	0 - 1 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8775P	2.668 ms	0 - 21 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS9075	2.611 ms	3 - 8 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.564 ms	0 - 30 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA7255P	4.826 ms	3 - 24 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8295P	3.38 ms	0 - 17 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.008 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.161 ms	0 - 22 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.248 ms	0 - 28 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS6490	1.217 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.918 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.381 ms	0 - 2 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8775P	0.606 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS9075	0.583 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCM6690	1.619 ms	0 - 18 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.532 ms	0 - 30 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA7255P	0.918 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8295P	0.767 ms	0 - 18 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.225 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.402 ms	0 - 18 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