EfficientNet-Lite4: Optimized for Qualcomm Devices

EfficientNet-Lite4 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-Lite4 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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit EfficientNet-Lite4 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-Lite4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

Input resolution: 300x300
Model checkpoint: Imagenet
Model size (float): 51.9 MB
Number of parameters: 13.01M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientNet-Lite4	ONNX	float	Snapdragon® X2 Elite	1.445 ms	1 - 1 MB	NPU
EfficientNet-Lite4	ONNX	float	Snapdragon® X Elite	2.721 ms	28 - 28 MB	NPU
EfficientNet-Lite4	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.902 ms	0 - 101 MB	NPU
EfficientNet-Lite4	ONNX	float	Snapdragon® 8 Gen 1 Mobile	5.534 ms	0 - 101 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	4.626 ms	1 - 5 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.626 ms	0 - 44 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® QCS8450	5.534 ms	0 - 101 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.143 ms	1 - 4 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	2.721 ms	28 - 28 MB	NPU
EfficientNet-Lite4	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.5 ms	0 - 56 MB	NPU
EfficientNet-Lite4	ONNX	float	Snapdragon® 8 Elite Mobile	1.5 ms	0 - 56 MB	NPU
EfficientNet-Lite4	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.148 ms	0 - 58 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® X2 Elite	0.648 ms	1 - 1 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® X Elite	1.279 ms	16 - 16 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.859 ms	0 - 110 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	2.082 ms	0 - 118 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	6.1 ms	0 - 3 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.337 ms	0 - 4 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.231 ms	0 - 18 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® QCS8450	2.082 ms	0 - 118 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.42 ms	0 - 3 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.279 ms	16 - 16 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	10.96 ms	0 - 194 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	1.611 ms	0 - 72 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.716 ms	0 - 72 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.716 ms	0 - 72 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.602 ms	0 - 74 MB	NPU
EfficientNet-Lite4	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.611 ms	0 - 72 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® X2 Elite	1.838 ms	1 - 1 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® X Elite	3.534 ms	1 - 1 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.199 ms	0 - 98 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	6.884 ms	0 - 99 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	4.837 ms	1 - 4 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	15.306 ms	1 - 54 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.139 ms	1 - 3 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® SA8775P	4.796 ms	1 - 54 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® SA8650P	4.796 ms	1 - 54 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® SA8255P	4.796 ms	1 - 54 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® QCS8450	6.884 ms	0 - 99 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	4.511 ms	1 - 4 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	3.534 ms	1 - 1 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.688 ms	0 - 55 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® SA7255P	15.306 ms	1 - 54 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Qualcomm® SA8295P	6.445 ms	1 - 50 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.688 ms	0 - 55 MB	NPU
EfficientNet-Lite4	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.267 ms	1 - 56 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.755 ms	0 - 0 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® X Elite	1.436 ms	0 - 0 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.908 ms	0 - 97 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	2.334 ms	0 - 106 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	7.091 ms	0 - 2 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.334 ms	0 - 3 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	3.376 ms	0 - 63 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.271 ms	0 - 2 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® SA8775P	1.603 ms	0 - 65 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® SA8650P	1.603 ms	0 - 65 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® SA8255P	1.603 ms	0 - 65 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® QCS8450	2.334 ms	0 - 106 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.43 ms	0 - 2 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.436 ms	0 - 0 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	11.276 ms	0 - 185 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	1.621 ms	0 - 65 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.653 ms	0 - 67 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® SA7255P	3.376 ms	0 - 63 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Qualcomm® SA8295P	2.529 ms	0 - 61 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.653 ms	0 - 67 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.528 ms	0 - 64 MB	NPU
EfficientNet-Lite4	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.621 ms	0 - 65 MB	NPU
EfficientNet-Lite4	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.185 ms	0 - 112 MB	NPU
EfficientNet-Lite4	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	6.678 ms	0 - 113 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	4.849 ms	0 - 33 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	15.31 ms	0 - 64 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.104 ms	0 - 3 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® SA8775P	4.802 ms	0 - 65 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® SA8650P	4.802 ms	0 - 65 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® SA8255P	4.802 ms	0 - 65 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® QCS8450	6.678 ms	0 - 113 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	4.551 ms	0 - 32 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.688 ms	0 - 68 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® SA7255P	15.31 ms	0 - 64 MB	NPU
EfficientNet-Lite4	TFLITE	float	Qualcomm® SA8295P	6.458 ms	0 - 48 MB	NPU
EfficientNet-Lite4	TFLITE	float	Snapdragon® 8 Elite Mobile	1.688 ms	0 - 68 MB	NPU
EfficientNet-Lite4	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.261 ms	0 - 67 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.656 ms	0 - 100 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	1.756 ms	0 - 103 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	5.79 ms	0 - 31 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.039 ms	0 - 18 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	2.801 ms	0 - 59 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.928 ms	0 - 2 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® SA8775P	1.273 ms	0 - 62 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® SA8650P	1.273 ms	0 - 62 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® SA8255P	1.273 ms	0 - 62 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® QCS8450	1.756 ms	0 - 103 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.085 ms	0 - 17 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	10.046 ms	0 - 178 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	1.241 ms	0 - 174 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.518 ms	0 - 58 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® SA7255P	2.801 ms	0 - 59 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Qualcomm® SA8295P	2.14 ms	0 - 56 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.518 ms	0 - 58 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.417 ms	0 - 62 MB	NPU
EfficientNet-Lite4	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.241 ms	0 - 174 MB	NPU

License

The license for the original implementation of EfficientNet-Lite4 can be found here.

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/EfficientNet-Lite4

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Paper • 1905.11946 • Published May 28, 2019 • 4