SESR-M5: Optimized for Qualcomm Devices

SESR M5 performs efficient on-device upscaling of images.

This is based on the implementation of SESR-M5 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 SESR-M5 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 SESR-M5 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.super_resolution

Model Stats:

• Model checkpoint: sesr_m5_3x_checkpoint
• Input resolution: 128x128
• Number of parameters: 343K
• Model size (float): 1.32 MB
• Model size (w8a8): 395 KB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
SESR-M5	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.971 ms	0 - 25 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Elite Mobile	1.205 ms	0 - 26 MB	NPU
SESR-M5	ONNX	float	Snapdragon® X2 Elite	1.146 ms	6 - 6 MB	NPU
SESR-M5	ONNX	float	Snapdragon® X Elite	2.196 ms	8 - 8 MB	NPU
SESR-M5	ONNX	float	Snapdragon® X Elite	2.196 ms	8 - 8 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.452 ms	0 - 35 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.999 ms	0 - 2 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS9075	3.219 ms	8 - 10 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.205 ms	0 - 26 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.378 ms	0 - 26 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.429 ms	0 - 27 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X2 Elite	0.407 ms	1 - 1 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X Elite	0.932 ms	3 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X Elite	0.932 ms	3 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.552 ms	0 - 33 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS6490	42.443 ms	38 - 41 MB	CPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.781 ms	0 - 2 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS9075	0.963 ms	0 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCM6690	30.929 ms	38 - 44 MB	CPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.429 ms	0 - 27 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	23.972 ms	38 - 45 MB	CPU
SESR-M5	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	23.972 ms	38 - 45 MB	CPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.868 ms	0 - 27 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.03 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X2 Elite	1.172 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X Elite	2.062 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X Elite	2.062 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.276 ms	0 - 35 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.542 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.863 ms	0 - 9 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8775P	3.025 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8775P	3.025 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8775P	3.025 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS9075	3.06 ms	0 - 5 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.772 ms	0 - 37 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA7255P	10.542 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8295P	3.488 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.03 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.292 ms	0 - 26 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.384 ms	0 - 28 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.45 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X Elite	0.736 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X Elite	0.736 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.44 ms	1 - 32 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS6490	2.661 ms	2 - 4 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.998 ms	0 - 23 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.6 ms	0 - 63 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8775P	0.828 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8775P	0.828 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8775P	0.828 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS9075	0.882 ms	0 - 2 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCM6690	6.819 ms	0 - 138 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.857 ms	0 - 33 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA7255P	1.998 ms	0 - 23 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8295P	1.327 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.384 ms	0 - 28 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.781 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.781 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.871 ms	0 - 28 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite Mobile	1.033 ms	0 - 25 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.278 ms	0 - 35 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8275 (Proxy)	10.564 ms	3 - 27 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.877 ms	0 - 4 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8775P	3.066 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8775P	3.066 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8775P	3.066 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS9075	3.056 ms	1 - 7 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.903 ms	0 - 37 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA7255P	10.564 ms	3 - 27 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8295P	3.465 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.033 ms	0 - 25 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.298 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.382 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.46 ms	0 - 32 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS6490	2.758 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.993 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.614 ms	0 - 2 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8775P	0.866 ms	0 - 25 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8775P	0.866 ms	0 - 25 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8775P	0.866 ms	0 - 25 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS9075	0.883 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCM6690	6.839 ms	1 - 135 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.864 ms	0 - 34 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA7255P	1.993 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8295P	1.342 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.382 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.789 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.789 ms	0 - 22 MB	NPU

License

• The license for the original implementation of SESR-M5 can be found here.

References

• Collapsible Linear Blocks for Super-Efficient Super Resolution
• Source Model Implementation

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.