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 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a8	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a8	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.42, TFLite 2.17.0	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® X Elite	2.261 ms	8 - 8 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.615 ms	0 - 101 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.321 ms	0 - 4 MB	NPU
SESR-M5	ONNX	float	Qualcomm® QCS9075	3.402 ms	7 - 10 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.315 ms	0 - 93 MB	NPU
SESR-M5	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.073 ms	0 - 92 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® X Elite	0.892 ms	3 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.748 ms	0 - 100 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS6490	42.249 ms	38 - 41 MB	CPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.953 ms	0 - 115 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCS9075	1.222 ms	0 - 3 MB	NPU
SESR-M5	ONNX	w8a8	Qualcomm® QCM6690	30.371 ms	36 - 43 MB	CPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.536 ms	0 - 90 MB	NPU
SESR-M5	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	22.496 ms	38 - 45 MB	CPU
SESR-M5	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.488 ms	0 - 94 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® X Elite	2.085 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.281 ms	0 - 35 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.536 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.911 ms	0 - 30 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8775P	3.023 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)	2.788 ms	0 - 38 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA7255P	10.536 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	float	Qualcomm® SA8295P	3.462 ms	0 - 21 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.035 ms	0 - 28 MB	NPU
SESR-M5	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.873 ms	0 - 27 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® X Elite	0.756 ms	0 - 0 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.446 ms	0 - 31 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS6490	2.729 ms	2 - 4 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.93 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.628 ms	0 - 2 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8775P	0.843 ms	0 - 23 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS9075	0.887 ms	0 - 2 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCM6690	6.844 ms	0 - 134 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.944 ms	0 - 33 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA7255P	1.93 ms	0 - 24 MB	NPU
SESR-M5	QNN_DLC	w8a8	Qualcomm® SA8295P	1.386 ms	0 - 19 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.384 ms	0 - 21 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.84 ms	0 - 21 MB	NPU
SESR-M5	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.316 ms	0 - 24 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.283 ms	0 - 35 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8275 (Proxy)	59.86 ms	3 - 21 MB	GPU
SESR-M5	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.872 ms	0 - 2 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA8775P	3.065 ms	0 - 26 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS9075	3.086 ms	3 - 9 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.8 ms	0 - 37 MB	NPU
SESR-M5	TFLITE	float	Qualcomm® SA7255P	59.86 ms	3 - 21 MB	GPU
SESR-M5	TFLITE	float	Qualcomm® SA8295P	3.441 ms	0 - 22 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.041 ms	0 - 24 MB	NPU
SESR-M5	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.874 ms	0 - 28 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.448 ms	0 - 31 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS6490	2.479 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.971 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.641 ms	0 - 69 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8775P	0.879 ms	0 - 24 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS9075	0.91 ms	0 - 3 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCM6690	6.848 ms	1 - 135 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.952 ms	0 - 32 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA7255P	1.971 ms	0 - 23 MB	NPU
SESR-M5	TFLITE	w8a8	Qualcomm® SA8295P	1.392 ms	0 - 20 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.383 ms	0 - 21 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.847 ms	0 - 21 MB	NPU
SESR-M5	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.315 ms	0 - 24 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.