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® X Elite	2.696 ms	46 - 46 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.831 ms	0 - 155 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.433 ms	0 - 50 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	3.452 ms	1 - 4 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.427 ms	0 - 77 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.181 ms	0 - 77 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X2 Elite	1.327 ms	47 - 47 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	2.674 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.575 ms	0 - 179 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	277.999 ms	26 - 31 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.379 ms	0 - 32 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	2.675 ms	0 - 3 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	125.041 ms	14 - 28 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.163 ms	0 - 126 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	114.755 ms	25 - 38 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.927 ms	0 - 127 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	1.089 ms	24 - 24 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	2.92 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.909 ms	0 - 143 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.809 ms	1 - 66 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.627 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	3.681 ms	3 - 5 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.632 ms	0 - 155 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.504 ms	1 - 71 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.203 ms	1 - 69 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	1.595 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	2.923 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.785 ms	0 - 148 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS6490	6.702 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.343 ms	0 - 105 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.62 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	2.945 ms	2 - 4 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	14.079 ms	0 - 226 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	3.226 ms	0 - 151 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.254 ms	0 - 106 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	2.864 ms	0 - 107 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.991 ms	0 - 108 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.418 ms	0 - 0 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.904 ms	0 - 190 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8275 (Proxy)	10.839 ms	0 - 111 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.603 ms	0 - 2 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	3.689 ms	0 - 50 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.686 ms	0 - 206 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.486 ms	0 - 114 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.206 ms	0 - 112 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.