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 2.45	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® 8 Elite Gen 5 Mobile	1.181 ms	0 - 76 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X2 Elite	1.318 ms	47 - 47 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X Elite	2.69 ms	46 - 46 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.826 ms	0 - 156 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.42 ms	0 - 52 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	3.473 ms	0 - 4 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.427 ms	0 - 70 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.932 ms	0 - 127 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	1.084 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	2.672 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.601 ms	0 - 180 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	284.749 ms	26 - 30 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.344 ms	0 - 32 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	2.68 ms	0 - 3 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	122.475 ms	17 - 30 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.15 ms	0 - 118 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	114.5 ms	26 - 39 MB	CPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.2 ms	1 - 68 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	1.572 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	2.892 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.93 ms	0 - 140 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.787 ms	1 - 63 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.6 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	3.64 ms	1 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.699 ms	0 - 148 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.501 ms	1 - 66 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.004 ms	0 - 118 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.464 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	2.907 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.785 ms	0 - 147 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS6490	6.541 ms	2 - 4 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.337 ms	0 - 105 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.626 ms	0 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	2.915 ms	2 - 4 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	14.068 ms	0 - 228 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	3.265 ms	0 - 149 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.234 ms	0 - 112 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	2.955 ms	0 - 105 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.198 ms	0 - 107 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.897 ms	0 - 182 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8275 (Proxy)	10.84 ms	0 - 104 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.636 ms	0 - 4 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	3.667 ms	0 - 50 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.672 ms	0 - 192 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.477 ms	0 - 110 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.