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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Swin-Small	ONNX	float	Snapdragon® X2 Elite	6.877 ms	2 - 2 MB	NPU
Swin-Small	ONNX	float	Snapdragon® X Elite	16.218 ms	101 - 101 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Gen 3 Mobile	10.147 ms	0 - 444 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Gen 1 Mobile	23.418 ms	1 - 432 MB	NPU
Swin-Small	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	15.546 ms	0 - 4 MB	NPU
Swin-Small	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.379 ms	0 - 114 MB	NPU
Swin-Small	ONNX	float	Qualcomm® QCS8450	23.418 ms	1 - 432 MB	NPU
Swin-Small	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	17.716 ms	1 - 4 MB	NPU
Swin-Small	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	16.218 ms	101 - 101 MB	NPU
Swin-Small	ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.811 ms	1 - 610 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Elite Mobile	7.811 ms	1 - 610 MB	NPU
Swin-Small	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.427 ms	1 - 622 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® X2 Elite	5.985 ms	1 - 1 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® X Elite	13.893 ms	54 - 54 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	8.726 ms	0 - 526 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	16.526 ms	0 - 437 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	40.392 ms	0 - 3 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	11.846 ms	0 - 4 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	13.291 ms	0 - 58 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® QCS8450	16.526 ms	0 - 437 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	13.995 ms	0 - 3 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	13.893 ms	54 - 54 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	56.588 ms	2 - 557 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	13.964 ms	0 - 388 MB	NPU
Swin-Small	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	6.859 ms	0 - 439 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Elite Mobile	6.859 ms	0 - 439 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	5.643 ms	0 - 449 MB	NPU
Swin-Small	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	13.964 ms	0 - 388 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® X2 Elite	7.129 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® X Elite	16.331 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.928 ms	1 - 407 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	23.881 ms	0 - 395 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	15.602 ms	1 - 4 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.337 ms	1 - 4 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8775P	17.421 ms	1 - 593 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8650P	17.421 ms	1 - 593 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8255P	17.421 ms	1 - 593 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® QCS8450	23.881 ms	0 - 395 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	17.63 ms	3 - 5 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	16.331 ms	1 - 1 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	7.594 ms	1 - 587 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA7255P	37.94 ms	1 - 275 MB	NPU
Swin-Small	QNN_DLC	float	Qualcomm® SA8295P	22.646 ms	1 - 270 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Elite Mobile	7.594 ms	1 - 587 MB	NPU
Swin-Small	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.247 ms	0 - 600 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® X2 Elite	7.251 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® X Elite	17.485 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	10.777 ms	0 - 870 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	14.372 ms	0 - 3 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	16.207 ms	0 - 3 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	16.763 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8650P	16.763 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA8255P	16.763 ms	0 - 638 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	17.054 ms	2 - 4 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	17.485 ms	0 - 0 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	73.029 ms	0 - 751 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	17.377 ms	0 - 652 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	8.085 ms	0 - 623 MB	NPU
Swin-Small	QNN_DLC	w8a16	Qualcomm® SA7255P	29.247 ms	0 - 636 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	8.085 ms	0 - 623 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	6.501 ms	0 - 640 MB	NPU
Swin-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	17.377 ms	0 - 652 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	10.181 ms	0 - 434 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	23.425 ms	0 - 411 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	15.575 ms	0 - 104 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.589 ms	0 - 4 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8775P	17.46 ms	0 - 306 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8650P	17.46 ms	0 - 306 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8255P	17.46 ms	0 - 306 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® QCS8450	23.425 ms	0 - 411 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	18.096 ms	0 - 104 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	7.797 ms	0 - 296 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA7255P	37.377 ms	0 - 303 MB	NPU
Swin-Small	TFLITE	float	Qualcomm® SA8295P	22.992 ms	0 - 297 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Elite Mobile	7.797 ms	0 - 296 MB	NPU
Swin-Small	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.599 ms	0 - 320 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.