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 2.45	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 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	0.434 ms	0 - 22 MB	NPU
XLSR	ONNX	float	Snapdragon® X2 Elite	0.409 ms	6 - 6 MB	NPU
XLSR	ONNX	float	Snapdragon® X Elite	1.077 ms	8 - 8 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.654 ms	0 - 29 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.97 ms	0 - 15 MB	NPU
XLSR	ONNX	float	Qualcomm® QCS9075	1.238 ms	8 - 11 MB	NPU
XLSR	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.511 ms	0 - 24 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.24 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® X2 Elite	0.242 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	0.363 ms	0 - 30 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS6490	11.679 ms	20 - 22 MB	CPU
XLSR	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.547 ms	0 - 23 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCS9075	0.702 ms	0 - 3 MB	NPU
XLSR	ONNX	w8a8	Qualcomm® QCM6690	8.444 ms	20 - 26 MB	CPU
XLSR	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.279 ms	0 - 19 MB	NPU
XLSR	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	6.435 ms	19 - 26 MB	CPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.328 ms	0 - 24 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X2 Elite	0.422 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® X Elite	0.908 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.461 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.179 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.763 ms	0 - 16 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8775P	1.159 ms	0 - 22 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS9075	1.108 ms	0 - 5 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.046 ms	0 - 30 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA7255P	2.179 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	float	Qualcomm® SA8295P	1.389 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.368 ms	0 - 26 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.18 ms	0 - 24 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.264 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® X Elite	0.505 ms	0 - 0 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.247 ms	0 - 30 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS6490	1.399 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.917 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.397 ms	0 - 1 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8775P	0.578 ms	0 - 22 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS9075	0.559 ms	0 - 2 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCM6690	1.6 ms	0 - 19 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.467 ms	0 - 29 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA7255P	0.917 ms	0 - 21 MB	NPU
XLSR	QNN_DLC	w8a8	Qualcomm® SA8295P	0.771 ms	0 - 18 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.212 ms	0 - 26 MB	NPU
XLSR	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.411 ms	0 - 20 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.792 ms	0 - 25 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.412 ms	0 - 31 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.701 ms	3 - 25 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.226 ms	0 - 7 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8775P	2.692 ms	0 - 23 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS9075	2.602 ms	3 - 8 MB	NPU
XLSR	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.518 ms	0 - 32 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA7255P	4.701 ms	3 - 25 MB	NPU
XLSR	TFLITE	float	Qualcomm® SA8295P	3.161 ms	0 - 18 MB	NPU
XLSR	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.976 ms	0 - 22 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.178 ms	0 - 24 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.262 ms	0 - 29 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS6490	1.066 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.962 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.403 ms	0 - 1 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8775P	0.614 ms	0 - 22 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS9075	0.579 ms	0 - 3 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCM6690	1.604 ms	0 - 18 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.474 ms	0 - 30 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA7255P	0.962 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Qualcomm® SA8295P	0.796 ms	0 - 18 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.225 ms	0 - 21 MB	NPU
XLSR	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.415 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