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 2.42, 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 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® 8 Elite Gen 5 Mobile	1.186 ms	0 - 76 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X2 Elite	1.322 ms	47 - 47 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X Elite	2.699 ms	46 - 46 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.819 ms	0 - 156 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.418 ms	0 - 52 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	3.456 ms	0 - 4 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.438 ms	0 - 78 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.915 ms	0 - 125 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	2.573 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	2.679 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.576 ms	0 - 180 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	282.139 ms	28 - 32 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.361 ms	0 - 33 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	2.698 ms	0 - 3 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	123.147 ms	42 - 55 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.159 ms	0 - 127 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	114.34 ms	27 - 41 MB	CPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.202 ms	1 - 69 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	1.624 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	2.921 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.925 ms	0 - 145 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.826 ms	1 - 66 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.618 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	3.715 ms	1 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.632 ms	0 - 154 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.488 ms	0 - 69 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.99 ms	0 - 109 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.875 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	2.939 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.775 ms	0 - 147 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS6490	6.663 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.361 ms	0 - 105 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.626 ms	0 - 156 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	2.937 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	14.189 ms	0 - 226 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	3.25 ms	0 - 152 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.252 ms	0 - 106 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	2.877 ms	0 - 102 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.203 ms	0 - 112 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.922 ms	0 - 197 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8275 (Proxy)	10.855 ms	0 - 112 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.609 ms	0 - 3 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	3.694 ms	0 - 50 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.69 ms	0 - 205 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.49 ms	0 - 114 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.