Beit: Optimized for Qualcomm Devices

Beit 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 Beit 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 1.25.0	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.25.0	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 Beit 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 Beit 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: 92.0M
• Model size (float): 351 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Beit	ONNX	float	Snapdragon® X2 Elite	7.441 ms	2 - 2 MB	NPU
Beit	ONNX	float	Snapdragon® X Elite	15.354 ms	184 - 184 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Gen 3 Mobile	10.47 ms	0 - 449 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Gen 1 Mobile	17.99 ms	0 - 421 MB	NPU
Beit	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.888 ms	0 - 63 MB	NPU
Beit	ONNX	float	Qualcomm® QCS8450	17.99 ms	0 - 421 MB	NPU
Beit	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	17.934 ms	0 - 4 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	7.169 ms	0 - 307 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Elite Mobile	8.582 ms	1 - 305 MB	NPU
Beit	ONNX	float	Qualcomm® Dragonwing™ Q-8750	8.582 ms	1 - 305 MB	NPU
Beit	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	15.354 ms	184 - 184 MB	NPU
Beit	ONNX	w8a16	Snapdragon® X2 Elite	2.669 ms	1 - 1 MB	NPU
Beit	ONNX	w8a16	Snapdragon® X Elite	6.898 ms	95 - 95 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	4.576 ms	0 - 422 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	6.678 ms	0 - 99 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	6.621 ms	0 - 3 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	9.054 ms	0 - 412 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.396 ms	0 - 257 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	109.293 ms	0 - 443 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 8 Elite Mobile	3.593 ms	0 - 361 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	9.054 ms	0 - 412 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	3.593 ms	0 - 361 MB	NPU
Beit	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	6.898 ms	95 - 95 MB	NPU
Beit	QNN_DLC	float	Snapdragon® X2 Elite	7.853 ms	1 - 1 MB	NPU
Beit	QNN_DLC	float	Snapdragon® X Elite	15.165 ms	1 - 1 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	10.476 ms	0 - 395 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	17.553 ms	0 - 380 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS8275	48.01 ms	1 - 295 MB	NPU
Beit	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.383 ms	1 - 3 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8775P	17.18 ms	1 - 295 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8650P	17.18 ms	1 - 295 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8255P	17.18 ms	1 - 295 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS8450	17.553 ms	0 - 380 MB	NPU
Beit	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	17.494 ms	3 - 5 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	7.184 ms	1 - 301 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA7255P	48.01 ms	1 - 295 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Elite Mobile	8.576 ms	1 - 301 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8295P	15.302 ms	1 - 289 MB	NPU
Beit	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	8.576 ms	1 - 301 MB	NPU
Beit	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	15.165 ms	1 - 1 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.19 ms	0 - 0 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® X Elite	7.332 ms	0 - 0 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.671 ms	0 - 413 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® QCS8275	15.088 ms	0 - 351 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	6.773 ms	0 - 2 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® SA8775P	7.054 ms	0 - 352 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® SA8650P	7.054 ms	0 - 352 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® SA8255P	7.054 ms	0 - 352 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	7.12 ms	0 - 2 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	8.687 ms	0 - 399 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.559 ms	0 - 245 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	109.915 ms	0 - 428 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® SA7255P	15.088 ms	0 - 351 MB	NPU
Beit	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	3.589 ms	0 - 349 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	8.687 ms	0 - 399 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	3.589 ms	0 - 349 MB	NPU
Beit	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	7.332 ms	0 - 0 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	10.515 ms	0 - 406 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	17.546 ms	0 - 371 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS8275	48.061 ms	0 - 300 MB	NPU
Beit	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.002 ms	0 - 3 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8775P	17.189 ms	0 - 301 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8650P	17.189 ms	0 - 301 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8255P	17.189 ms	0 - 301 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS8450	17.546 ms	0 - 371 MB	NPU
Beit	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	17.528 ms	0 - 186 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	7.18 ms	0 - 311 MB	NPU
Beit	TFLITE	float	Qualcomm® SA7255P	48.061 ms	0 - 300 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Elite Mobile	8.573 ms	0 - 311 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8295P	15.345 ms	0 - 293 MB	NPU
Beit	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	8.573 ms	0 - 311 MB	NPU

License

• The license for the original implementation of Beit can be found here.

References

• BEIT: BERT Pre-Training of Image Transformers
• 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.