SwinV2-Base: Optimized for Qualcomm Devices

SwinV2Base is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of SwinV2-Base 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
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit SwinV2-Base 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 SwinV2-Base on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 256x256
• Number of parameters: 88.8M
• Model size (float): 339 MB
• Model size (w8a16): 90.2 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	11.408 ms	1 - 422 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Elite Mobile	14.689 ms	1 - 392 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® X2 Elite	12.424 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® X Elite	28.891 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® X Elite	28.891 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.653 ms	0 - 544 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	27.776 ms	1 - 3 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8775P	31.575 ms	1 - 388 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8775P	31.575 ms	1 - 388 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8775P	31.575 ms	1 - 388 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA7255P	73.913 ms	1 - 393 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	41.638 ms	0 - 533 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8295P	37.879 ms	1 - 377 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	14.689 ms	1 - 392 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® QCS9075	36.63 ms	1 - 3 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	11.355 ms	0 - 941 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	14.721 ms	0 - 910 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	12.14 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® X Elite	30.726 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® X Elite	30.726 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	19.647 ms	0 - 2033 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	29.236 ms	0 - 4 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA8775P	29.668 ms	0 - 905 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA8775P	29.668 ms	0 - 905 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA8775P	29.668 ms	0 - 905 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA7255P	52.656 ms	0 - 486 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	14.721 ms	0 - 910 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® QCS9075	34.261 ms	0 - 2 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	11.338 ms	0 - 930 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Elite Mobile	14.958 ms	0 - 901 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	20.027 ms	0 - 2178 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® QCS8550 (Proxy)	29.487 ms	0 - 5 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8775P	32.53 ms	0 - 879 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8775P	32.53 ms	0 - 879 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8775P	32.53 ms	0 - 879 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA7255P	71.111 ms	0 - 884 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® QCS8450 (Proxy)	42.631 ms	0 - 676 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8295P	40.646 ms	0 - 875 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	14.958 ms	0 - 901 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® QCS9075	36.579 ms	0 - 180 MB	NPU

License

• The license for the original implementation of SwinV2-Base can be found here.

References

• Swin Transformer V2: Scaling Up Capacity and 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.