Swin-Small: Optimized for Qualcomm Devices

SwinSmall 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 Swin-Small 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	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	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 Swin-Small 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 Swin-Small on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 224x224
• Number of parameters: 50.4M
• Model size (float): 193 MB
• Model size (w8a16): 52.5 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Swin-Small	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.318 ms	1 - 647 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Elite Mobile	7.658 ms	1 - 645 MB	NPU
Swin-Small	ONNX	float	Snapdragon® X2 Elite	6.719 ms	101 - 101 MB	NPU
Swin-Small	ONNX	float	Snapdragon® X Elite	15.881 ms	100 - 100 MB	NPU
Swin-Small	ONNX	float	Snapdragon® X Elite	15.881 ms	100 - 100 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.989 ms	0 - 519 MB	NPU
Swin-Small	ONNX	float	Qualcomm® QCS8550 (Proxy)	15.343 ms	1 - 7 MB	NPU
Swin-Small	ONNX	float	Qualcomm® QCS9075	19.924 ms	0 - 4 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.658 ms	1 - 645 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	5.887 ms	0 - 382 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Elite Mobile	7.337 ms	0 - 458 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® X2 Elite	6.325 ms	54 - 54 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® X Elite	14.567 ms	53 - 53 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® X Elite	14.567 ms	53 - 53 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	9.211 ms	0 - 528 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® QCS6490	721.617 ms	94 - 109 MB	CPU
Swin-Small	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	13.958 ms	0 - 62 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® QCS9075	16.989 ms	0 - 3 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® QCM6690	379.333 ms	75 - 94 MB	CPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	7.337 ms	0 - 458 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	355.219 ms	92 - 113 MB	CPU
Swin-Small	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	355.219 ms	92 - 113 MB	CPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.215 ms	1 - 597 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Elite Mobile	7.594 ms	1 - 587 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® X2 Elite	6.995 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® X Elite	16.25 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® X Elite	16.25 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.901 ms	0 - 407 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	37.927 ms	1 - 275 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	15.348 ms	1 - 16 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8775P	17.375 ms	1 - 592 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8775P	17.375 ms	1 - 592 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8775P	17.375 ms	1 - 592 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® QCS9075	19.447 ms	1 - 3 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	23.957 ms	0 - 397 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA7255P	37.927 ms	1 - 275 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8295P	22.613 ms	1 - 269 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	7.594 ms	1 - 587 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	6.384 ms	0 - 635 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	8.047 ms	0 - 622 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® X2 Elite	7.168 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® X Elite	17.272 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® X Elite	17.272 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	10.729 ms	0 - 864 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	29.077 ms	0 - 634 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	16.261 ms	0 - 3 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	16.636 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	16.636 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	16.636 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® QCS9075	18.784 ms	0 - 2 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® QCM6690	65.314 ms	0 - 617 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA7255P	29.077 ms	0 - 634 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	8.047 ms	0 - 622 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	16.993 ms	0 - 654 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	16.993 ms	0 - 654 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.528 ms	0 - 310 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Elite Mobile	7.798 ms	0 - 284 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	10.168 ms	0 - 436 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® QCS8275 (Proxy)	37.447 ms	0 - 301 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® QCS8550 (Proxy)	15.622 ms	0 - 4 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8775P	17.463 ms	0 - 305 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8775P	17.463 ms	0 - 305 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8775P	17.463 ms	0 - 305 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® QCS9075	19.903 ms	0 - 104 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® QCS8450 (Proxy)	23.5 ms	0 - 410 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA7255P	37.447 ms	0 - 301 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8295P	22.961 ms	0 - 296 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	7.798 ms	0 - 284 MB	NPU

License

• The license for the original implementation of Swin-Small can be found here.

References

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• 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.