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 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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	1.187 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	2.707 ms	46 - 46 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.831 ms	0 - 156 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.434 ms	0 - 51 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	3.451 ms	0 - 4 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.442 ms	0 - 78 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.923 ms	0 - 127 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	1.088 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	2.676 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.611 ms	0 - 178 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	276.246 ms	26 - 31 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.352 ms	0 - 32 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	2.695 ms	0 - 3 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	123.788 ms	15 - 28 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.149 ms	0 - 118 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	114.878 ms	26 - 39 MB	CPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.209 ms	1 - 70 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	1.631 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	2.922 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.92 ms	0 - 145 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.79 ms	1 - 67 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.622 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	3.686 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	1.494 ms	1 - 71 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.992 ms	0 - 109 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.419 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	2.914 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.779 ms	0 - 148 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS6490	6.781 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.323 ms	0 - 105 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.609 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	2.942 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	14.01 ms	0 - 226 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	3.187 ms	0 - 153 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	2.96 ms	0 - 106 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.205 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)	10.839 ms	0 - 112 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.611 ms	0 - 3 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	3.683 ms	0 - 50 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.643 ms	0 - 204 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.494 ms	0 - 118 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.