EfficientNet-V2-s: Optimized for Qualcomm Devices

EfficientNetV2-s 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-V2-s 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 EfficientNet-V2-s 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-V2-s on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 384x384
• Number of parameters: 21.4M
• Model size (float): 81.7 MB
• Model size (w8a16): 27.2 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientNet-V2-s	ONNX	float	Snapdragon® X2 Elite	4.395 ms	211 - 211 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X Elite	5.638 ms	147 - 147 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 3 Mobile	4.06 ms	1 - 155 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 1 Mobile	11.678 ms	2 - 187 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8550 (Proxy)	5.373 ms	0 - 51 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8450	11.678 ms	2 - 187 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite Mobile	3.087 ms	2 - 201 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.239 ms	1 - 201 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	8.06 ms	2 - 47 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8750	3.087 ms	2 - 201 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS7181	5.638 ms	147 - 147 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	2.367 ms	212 - 212 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	5.711 ms	181 - 181 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.642 ms	0 - 198 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	6.694 ms	1 - 208 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	17.251 ms	1 - 46 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.464 ms	0 - 34 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8450	6.694 ms	1 - 208 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	5.976 ms	1 - 46 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.002 ms	1 - 163 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.511 ms	0 - 164 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6.435 ms	1 - 269 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	34.927 ms	0 - 269 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS7790	6.435 ms	1 - 269 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8750	2.511 ms	0 - 164 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS7181	5.711 ms	181 - 181 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	3.443 ms	2 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	6.425 ms	2 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	4.337 ms	0 - 157 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	13.461 ms	0 - 187 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275	25.746 ms	2 - 75 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	5.83 ms	2 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8450	13.461 ms	0 - 187 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Mobile	3.137 ms	0 - 78 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® SA8295P	13.026 ms	2 - 106 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.286 ms	2 - 84 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® SA7255P	25.746 ms	2 - 75 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	8.747 ms	4 - 7 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8750	3.137 ms	0 - 78 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS7181	6.425 ms	2 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.877 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	6.792 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.2 ms	0 - 175 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	8.093 ms	0 - 186 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS6490	18.716 ms	1 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8275	12.095 ms	1 - 134 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	6.261 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450	8.093 ms	0 - 186 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	6.908 ms	1 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.227 ms	1 - 146 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	2.803 ms	0 - 145 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® SA8295P	8.376 ms	1 - 134 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	6.998 ms	1 - 254 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	41.701 ms	1 - 255 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® SA7255P	12.095 ms	1 - 134 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS7790	6.998 ms	1 - 254 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8750	2.803 ms	0 - 145 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS7181	6.792 ms	1 - 1 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	4.325 ms	0 - 200 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	13.45 ms	0 - 230 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8275	25.823 ms	0 - 116 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	5.771 ms	0 - 3 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® SA8775P	39.37 ms	0 - 33 MB	GPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® SA8650P	39.37 ms	0 - 33 MB	GPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® SA8255P	39.37 ms	0 - 33 MB	GPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450	13.45 ms	0 - 230 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Mobile	3.133 ms	0 - 124 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® SA8295P	13.002 ms	0 - 148 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.258 ms	0 - 120 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® SA7255P	25.823 ms	0 - 116 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	8.767 ms	0 - 51 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8750	3.133 ms	0 - 124 MB	NPU

License

• The license for the original implementation of EfficientNet-V2-s can be found here.

References

• EfficientNetV2: Smaller Models and Faster Training
• 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.