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® 8 Elite Gen 5 Mobile	0.435 ms	0 - 22 MB	NPU
XLSR	ONNX	float	Snapdragon® X2 Elite	0.443 ms	7 - 7 MB	NPU
XLSR	ONNX	float	Snapdragon® X Elite	1.064 ms	8 - 8 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.643 ms	0 - 29 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.965 ms	0 - 10 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS9075	1.246 ms	6 - 9 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.54 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.245 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X2 Elite	0.241 ms	1 - 1 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X Elite	0.652 ms	3 - 3 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.348 ms	0 - 29 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS6490	12.179 ms	20 - 22 MB	CPU
XLSR	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.547 ms	0 - 2 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS9075	0.691 ms	0 - 3 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCM6690	8.48 ms	19 - 25 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	6.158 ms	19 - 25 MB	CPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.327 ms	0 - 25 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X2 Elite	0.402 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X Elite	0.893 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.465 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.158 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.783 ms	0 - 1 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8775P	1.144 ms	0 - 22 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS9075	1.115 ms	0 - 5 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.044 ms	0 - 30 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA7255P	2.158 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8295P	1.387 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.361 ms	0 - 25 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.167 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.254 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X Elite	0.499 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.248 ms	0 - 27 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS6490	1.402 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.929 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.396 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8775P	0.575 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS9075	0.526 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCM6690	1.658 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.52 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA7255P	0.929 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8295P	0.779 ms	0 - 17 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.196 ms	0 - 23 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.402 ms	0 - 18 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.827 ms	0 - 22 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.459 ms	0 - 29 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.825 ms	3 - 24 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.233 ms	0 - 1 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8775P	2.708 ms	0 - 21 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS9075	2.613 ms	1 - 6 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.564 ms	0 - 29 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA7255P	4.825 ms	3 - 24 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8295P	3.343 ms	0 - 17 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.002 ms	0 - 24 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.16 ms	0 - 22 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.236 ms	0 - 29 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS6490	1.181 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.914 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.385 ms	0 - 1 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8775P	0.597 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS9075	0.577 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCM6690	1.622 ms	0 - 18 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.529 ms	0 - 30 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA7255P	0.914 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8295P	0.771 ms	0 - 17 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.212 ms	0 - 20 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.402 ms	0 - 19 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