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 2.42, 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 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	0.247 ms	5 - 5 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® X Elite	0.667 ms	5 - 5 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.354 ms	0 - 45 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.548 ms	0 - 2 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS9075	0.759 ms	1 - 3 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.283 ms	0 - 33 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.244 ms	0 - 33 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® X2 Elite	0.449 ms	1 - 1 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® X Elite	0.996 ms	1 - 1 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.553 ms	0 - 45 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.097 ms	1 - 30 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.853 ms	1 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA8775P	1.141 ms	1 - 32 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS9075	0.992 ms	1 - 3 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.583 ms	0 - 47 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA7255P	2.097 ms	1 - 30 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA8295P	1.48 ms	0 - 29 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.427 ms	0 - 30 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.33 ms	1 - 34 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	0.97 ms	0 - 0 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.563 ms	0 - 37 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS6490	2.289 ms	2 - 4 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	1.72 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.805 ms	0 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	1.008 ms	0 - 27 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS9075	0.963 ms	0 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCM6690	2.792 ms	0 - 140 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.981 ms	0 - 39 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA7255P	1.72 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA8295P	1.378 ms	0 - 23 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.377 ms	0 - 24 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.789 ms	0 - 25 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.31 ms	0 - 28 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.559 ms	0 - 45 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.18 ms	0 - 31 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.857 ms	0 - 2 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8775P	1.179 ms	0 - 33 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS9075	1.021 ms	0 - 8 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.609 ms	0 - 49 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA7255P	2.18 ms	0 - 31 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8295P	1.516 ms	0 - 30 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.436 ms	0 - 36 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.344 ms	0 - 36 MB	NPU

License

• The license for the original implementation of MobileNet-v3-Small can be found here.

References

• Searching for MobileNetV3
• 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.