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 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	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:

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

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 For Galaxy Mobile	11.089 ms	0 - 395 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	14.317 ms	1 - 370 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® X2 Elite	11.698 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® X Elite	28.646 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.489 ms	1 - 524 MB	NPU
SwinV2-Base	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	39.059 ms	0 - 505 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	29.183 ms	1 - 4 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	27.535 ms	1 - 527 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8650P	31.465 ms	1 - 388 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8255P	31.465 ms	1 - 388 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® QCS8450	39.059 ms	0 - 505 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	31.001 ms	1 - 3 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	28.646 ms	1 - 1 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	14.317 ms	1 - 370 MB	NPU
SwinV2-Base	QNN_DLC	float	Qualcomm® SA8295P	37.781 ms	1 - 357 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	9.967 ms	0 - 506 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	12.916 ms	0 - 446 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	10.431 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® X Elite	26.93 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	18.135 ms	0 - 570 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	23.322 ms	0 - 3 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	25.824 ms	0 - 3 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA8650P	30.025 ms	0 - 869 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® SA8255P	30.025 ms	0 - 869 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	25.814 ms	0 - 3 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	26.93 ms	0 - 0 MB	NPU
SwinV2-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	12.916 ms	0 - 446 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	11.303 ms	0 - 564 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	14.577 ms	0 - 451 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	20.082 ms	0 - 592 MB	NPU
SwinV2-Base	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	40.437 ms	0 - 604 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	29.439 ms	0 - 181 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	29.522 ms	0 - 4 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8650P	32.539 ms	0 - 878 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8255P	32.539 ms	0 - 878 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® QCS8450	40.437 ms	0 - 604 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	32.065 ms	0 - 181 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	14.577 ms	0 - 451 MB	NPU
SwinV2-Base	TFLITE	float	Qualcomm® SA8295P	39.519 ms	0 - 421 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.