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 2.43	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 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	0.979 ms	0 - 25 MB	NPU
SESR-M5	ONNX	float	Snapdragon® X2 Elite	1.156 ms	6 - 6 MB	NPU
SESR-M5	ONNX	float	Snapdragon® X Elite	2.188 ms	8 - 8 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.455 ms	0 - 35 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.999 ms	0 - 36 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS9075	3.204 ms	6 - 9 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.206 ms	0 - 21 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.371 ms	0 - 26 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X2 Elite	0.406 ms	1 - 1 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X Elite	0.922 ms	3 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.555 ms	0 - 33 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS6490	42.751 ms	38 - 41 MB	CPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.786 ms	0 - 2 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS9075	0.982 ms	0 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCM6690	31.018 ms	38 - 44 MB	CPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.426 ms	0 - 22 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	24.078 ms	38 - 45 MB	CPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.872 ms	0 - 27 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X2 Elite	1.192 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X Elite	2.074 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)	10.547 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.863 ms	0 - 2 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8775P	3.03 ms	0 - 25 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS9075	3.056 ms	2 - 7 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.791 ms	0 - 38 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA7255P	10.547 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8295P	3.461 ms	0 - 21 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.045 ms	0 - 28 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.31 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.567 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X Elite	0.764 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.44 ms	0 - 31 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS6490	2.716 ms	2 - 4 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.922 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.618 ms	0 - 1 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8775P	0.855 ms	0 - 23 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS9075	0.888 ms	0 - 2 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCM6690	6.83 ms	0 - 134 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.941 ms	0 - 32 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA7255P	1.922 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8295P	1.411 ms	0 - 20 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.383 ms	0 - 22 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.831 ms	0 - 21 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.866 ms	0 - 28 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)	10.555 ms	3 - 27 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.88 ms	0 - 18 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8775P	3.081 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS9075	3.091 ms	3 - 9 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.789 ms	0 - 38 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA7255P	10.555 ms	3 - 27 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8295P	3.508 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.044 ms	0 - 28 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.316 ms	0 - 24 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.46 ms	0 - 31 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS6490	2.572 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.963 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.639 ms	0 - 62 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8775P	0.88 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS9075	0.905 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCM6690	6.844 ms	1 - 135 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.954 ms	0 - 32 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA7255P	1.963 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8295P	1.415 ms	0 - 19 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.38 ms	0 - 21 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.844 ms	0 - 20 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.