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 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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® X Elite	13.672 ms	185 - 185 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.267 ms	0 - 526 MB	NPU
Beit	ONNX	float	Qualcomm® QCS8550 (Proxy)	12.916 ms	0 - 195 MB	NPU
Beit	ONNX	float	Qualcomm® QCS9075	17.716 ms	0 - 4 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	6.659 ms	0 - 485 MB	NPU
Beit	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.231 ms	1 - 487 MB	NPU
Beit	ONNX	float	Snapdragon® X2 Elite	5.992 ms	185 - 185 MB	NPU
Beit	ONNX	w8a16	Snapdragon® X Elite	12.517 ms	96 - 96 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	7.96 ms	0 - 496 MB	NPU
Beit	ONNX	w8a16	Qualcomm® QCS6490	1065.211 ms	44 - 67 MB	CPU
Beit	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	11.768 ms	0 - 117 MB	NPU
Beit	ONNX	w8a16	Qualcomm® QCS9075	14.318 ms	0 - 3 MB	NPU
Beit	ONNX	w8a16	Qualcomm® QCM6690	603.561 ms	72 - 83 MB	CPU
Beit	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	6.09 ms	0 - 401 MB	NPU
Beit	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	580.937 ms	70 - 83 MB	CPU
Beit	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.18 ms	0 - 406 MB	NPU
Beit	ONNX	w8a16	Snapdragon® X2 Elite	4.363 ms	96 - 96 MB	NPU
Beit	QNN_DLC	float	Snapdragon® X Elite	13.411 ms	1 - 1 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	8.721 ms	0 - 531 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	44.942 ms	1 - 485 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	12.631 ms	1 - 3 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8775P	16.437 ms	1 - 485 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS9075	16.769 ms	1 - 3 MB	NPU
Beit	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	22.952 ms	1 - 508 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA7255P	44.942 ms	1 - 485 MB	NPU
Beit	QNN_DLC	float	Qualcomm® SA8295P	19.056 ms	1 - 468 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	6.918 ms	1 - 480 MB	NPU
Beit	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.579 ms	0 - 480 MB	NPU
Beit	QNN_DLC	float	Snapdragon® X2 Elite	6.925 ms	1 - 1 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	6.661 ms	0 - 343 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS8275 (Proxy)	38.573 ms	0 - 297 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS8550 (Proxy)	9.321 ms	0 - 3 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8775P	12.133 ms	0 - 306 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS9075	13.714 ms	0 - 187 MB	NPU
Beit	TFLITE	float	Qualcomm® QCS8450 (Proxy)	19.347 ms	0 - 431 MB	NPU
Beit	TFLITE	float	Qualcomm® SA7255P	38.573 ms	0 - 297 MB	NPU
Beit	TFLITE	float	Qualcomm® SA8295P	16.021 ms	0 - 406 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.698 ms	0 - 297 MB	NPU
Beit	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.973 ms	0 - 297 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.