Swin-Base: Optimized for Qualcomm Devices

SwinBase 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-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
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-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 Swin-Base 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): 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
Swin-Base	ONNX	float	Snapdragon® X2 Elite	8.375 ms	2 - 2 MB	NPU
Swin-Base	ONNX	float	Snapdragon® X Elite	19.953 ms	175 - 175 MB	NPU
Swin-Base	ONNX	float	Snapdragon® 8 Gen 3 Mobile	13.224 ms	0 - 548 MB	NPU
Swin-Base	ONNX	float	Snapdragon® 8 Gen 1 Mobile	29.344 ms	1 - 1066 MB	NPU
Swin-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	21.348 ms	0 - 4 MB	NPU
Swin-Base	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	19.297 ms	0 - 195 MB	NPU
Swin-Base	ONNX	float	Qualcomm® QCS8450	29.344 ms	1 - 1066 MB	NPU
Swin-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	22.606 ms	1 - 4 MB	NPU
Swin-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	19.953 ms	175 - 175 MB	NPU
Swin-Base	ONNX	float	Qualcomm® Dragonwing™ Q-8750	9.91 ms	0 - 401 MB	NPU
Swin-Base	ONNX	float	Snapdragon® 8 Elite Mobile	9.91 ms	0 - 401 MB	NPU
Swin-Base	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	8.179 ms	1 - 423 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® X2 Elite	7.001 ms	1 - 1 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® X Elite	16.263 ms	92 - 92 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	10.468 ms	0 - 537 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	20.772 ms	0 - 536 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	58.018 ms	0 - 3 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	14.352 ms	0 - 4 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.395 ms	0 - 99 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® QCS8450	20.772 ms	0 - 536 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	16.13 ms	0 - 3 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	16.263 ms	92 - 92 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	107.798 ms	0 - 690 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	17.738 ms	0 - 620 MB	NPU
Swin-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	8.144 ms	0 - 417 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® 8 Elite Mobile	8.144 ms	0 - 417 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	6.538 ms	0 - 431 MB	NPU
Swin-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	17.738 ms	0 - 620 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® X2 Elite	8.443 ms	1 - 1 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® X Elite	19.307 ms	1 - 1 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	12.414 ms	0 - 515 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	28.86 ms	0 - 502 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	20.32 ms	1 - 4 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	53.605 ms	1 - 363 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	18.378 ms	1 - 419 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® SA8775P	21.415 ms	1 - 362 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® SA8650P	21.415 ms	1 - 362 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® SA8255P	21.415 ms	1 - 362 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® QCS8450	28.86 ms	0 - 502 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	21.549 ms	3 - 5 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	19.307 ms	1 - 1 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	9.29 ms	1 - 367 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® SA7255P	53.605 ms	1 - 363 MB	NPU
Swin-Base	QNN_DLC	float	Qualcomm® SA8295P	27.595 ms	1 - 353 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® 8 Elite Mobile	9.29 ms	1 - 367 MB	NPU
Swin-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	7.549 ms	0 - 385 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	8.513 ms	0 - 0 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® X Elite	20.547 ms	0 - 0 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	12.763 ms	0 - 508 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	17.37 ms	0 - 3 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	35.41 ms	0 - 412 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	19.157 ms	0 - 2 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® SA8775P	19.602 ms	0 - 412 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® SA8650P	19.602 ms	0 - 412 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® SA8255P	19.602 ms	0 - 412 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	24.464 ms	0 - 2 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	20.547 ms	0 - 0 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	123.253 ms	0 - 934 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	21.646 ms	0 - 603 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	9.537 ms	0 - 404 MB	NPU
Swin-Base	QNN_DLC	w8a16	Qualcomm® SA7255P	35.41 ms	0 - 412 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	9.537 ms	0 - 404 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	7.608 ms	0 - 423 MB	NPU
Swin-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	21.646 ms	0 - 603 MB	NPU
Swin-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	12.73 ms	0 - 1052 MB	NPU
Swin-Base	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	28.87 ms	0 - 512 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	20.923 ms	0 - 179 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	53.494 ms	0 - 709 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	18.814 ms	0 - 4 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® SA8775P	21.931 ms	0 - 375 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® SA8650P	21.931 ms	0 - 375 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® SA8255P	21.931 ms	0 - 375 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® QCS8450	28.87 ms	0 - 512 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	27.028 ms	0 - 178 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	9.644 ms	0 - 378 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® SA7255P	53.494 ms	0 - 709 MB	NPU
Swin-Base	TFLITE	float	Qualcomm® SA8295P	28.394 ms	0 - 371 MB	NPU
Swin-Base	TFLITE	float	Snapdragon® 8 Elite Mobile	9.644 ms	0 - 378 MB	NPU
Swin-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.942 ms	0 - 399 MB	NPU

License

• The license for the original implementation of Swin-Base 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.