EfficientNet-B0: Optimized for Qualcomm Devices

EfficientNetB0 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 EfficientNet-B0 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 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a16	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a16	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit EfficientNet-B0 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 EfficientNet-B0 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: 5.27M
• Model size (float): 20.1 MB
• Model size (w8a16): 6.99 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.391 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.063 ms	0 - 134 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.402 ms	0 - 24 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS9075	1.877 ms	1 - 3 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.839 ms	0 - 108 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.659 ms	0 - 107 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.618 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.155 ms	0 - 146 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS6490	122.425 ms	42 - 44 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	1.634 ms	0 - 10 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS9075	1.851 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCM6690	66.291 ms	42 - 51 MB	CPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.816 ms	0 - 124 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	54.16 ms	49 - 58 MB	CPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.699 ms	0 - 123 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.756 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.076 ms	0 - 63 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	4.898 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.554 ms	1 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	8.846 ms	1 - 39 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS9075	1.857 ms	3 - 5 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.601 ms	0 - 73 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA7255P	4.898 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8295P	3.614 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.806 ms	1 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.614 ms	1 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.896 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.126 ms	0 - 65 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS6490	4.316 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	3.293 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	1.677 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.944 ms	0 - 49 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS9075	1.857 ms	2 - 4 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCM6690	6.533 ms	0 - 163 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.977 ms	0 - 67 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA7255P	3.293 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8295P	2.358 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.783 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.674 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.639 ms	0 - 48 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.073 ms	0 - 77 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.911 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.542 ms	0 - 131 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	8.913 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS9075	1.877 ms	0 - 16 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.616 ms	0 - 80 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA7255P	4.911 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8295P	3.657 ms	0 - 52 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.811 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.612 ms	0 - 50 MB	NPU

License

• The license for the original implementation of EfficientNet-B0 can be found here.

References

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• 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.