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® X2 Elite	1.322 ms	47 - 47 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® X Elite	2.689 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)	2.428 ms	0 - 50 MB	NPU
EfficientNet-V2-s	ONNX	float	Qualcomm® QCS9075	3.451 ms	1 - 4 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.43 ms	0 - 70 MB	NPU
EfficientNet-V2-s	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.184 ms	0 - 76 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X2 Elite	1.091 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® X Elite	2.667 ms	24 - 24 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.593 ms	0 - 178 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS6490	281.17 ms	26 - 30 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.367 ms	0 - 32 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCS9075	2.671 ms	0 - 3 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Qualcomm® QCM6690	124.358 ms	14 - 27 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.148 ms	0 - 126 MB	NPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	114.091 ms	27 - 41 MB	CPU
EfficientNet-V2-s	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.93 ms	0 - 128 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X2 Elite	1.586 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® X Elite	2.93 ms	1 - 1 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.929 ms	0 - 144 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	10.806 ms	1 - 66 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.613 ms	1 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS9075	3.678 ms	1 - 3 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.717 ms	0 - 155 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.53 ms	0 - 68 MB	NPU
EfficientNet-V2-s	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.209 ms	1 - 70 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.416 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® X Elite	2.927 ms	0 - 0 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.784 ms	0 - 146 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)	5.367 ms	0 - 105 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.606 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS9075	2.944 ms	0 - 2 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCM6690	14.112 ms	0 - 226 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	3.168 ms	0 - 151 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.246 ms	0 - 106 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	2.988 ms	0 - 106 MB	NPU
EfficientNet-V2-s	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.994 ms	0 - 109 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.921 ms	0 - 196 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8275 (Proxy)	10.793 ms	0 - 111 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.621 ms	0 - 3 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS9075	3.687 ms	0 - 50 MB	NPU
EfficientNet-V2-s	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.619 ms	0 - 205 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.495 ms	0 - 113 MB	NPU
EfficientNet-V2-s	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.203 ms	0 - 113 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.