MobileNet-v3-Small: Optimized for Qualcomm Devices

MobileNetV3Small 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 MobileNet-v3-Small 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 1.25.0	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 MobileNet-v3-Small 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 MobileNet-v3-Small on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

Model checkpoint: Imagenet
Input resolution: 224x224
Number of parameters: 2.54M
Model size (float): 9.71 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MobileNet-v3-Small	ONNX	float	Snapdragon® X2 Elite	0.262 ms	212 - 212 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® X Elite	0.558 ms	148 - 148 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.35 ms	0 - 34 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.868 ms	1 - 43 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.561 ms	0 - 12 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS8450	0.868 ms	1 - 43 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite Mobile	0.286 ms	0 - 29 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.243 ms	1 - 26 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS9075	0.769 ms	0 - 51 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS8750	0.286 ms	0 - 29 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS7181	0.558 ms	148 - 148 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® X2 Elite	0.435 ms	1 - 1 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® X Elite	0.977 ms	1 - 1 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.552 ms	0 - 43 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.573 ms	0 - 49 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8275	2.073 ms	1 - 29 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.827 ms	1 - 65 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8450	1.573 ms	0 - 49 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.412 ms	0 - 28 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA8295P	1.462 ms	0 - 29 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.317 ms	1 - 30 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA7255P	2.073 ms	1 - 29 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS9075	0.984 ms	3 - 5 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8750	0.412 ms	0 - 28 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS7181	0.977 ms	1 - 1 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.427 ms	0 - 0 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® X Elite	0.924 ms	0 - 0 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.546 ms	0 - 39 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	0.984 ms	0 - 45 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS6490	2.321 ms	2 - 4 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8275	1.692 ms	0 - 28 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.79 ms	0 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8450	0.984 ms	0 - 45 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS9075	0.947 ms	2 - 4 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.309 ms	0 - 27 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.369 ms	0 - 31 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA8295P	1.286 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.798 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCM6690	2.826 ms	0 - 142 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA7255P	1.692 ms	0 - 28 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS7790	0.798 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8750	0.369 ms	0 - 31 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS7181	0.924 ms	0 - 0 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.554 ms	0 - 45 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.594 ms	0 - 50 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8275	2.169 ms	0 - 29 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.841 ms	0 - 8 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8775P	2.189 ms	0 - 30 MB	GPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8650P	2.189 ms	0 - 30 MB	GPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8255P	2.189 ms	0 - 30 MB	GPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8450	1.594 ms	0 - 50 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite Mobile	0.426 ms	0 - 30 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8295P	1.501 ms	0 - 29 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.323 ms	0 - 31 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA7255P	2.169 ms	0 - 29 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS9075	1.02 ms	0 - 8 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8750	0.426 ms	0 - 30 MB	NPU

License

The license for the original implementation of MobileNet-v3-Small 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

Model tree for qualcomm/MobileNet-v3-Small

Quantizations

1 model

Paper for qualcomm/MobileNet-v3-Small

Searching for MobileNetV3

Paper • 1905.02244 • Published May 6, 2019