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 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a16	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a16	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, 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® X Elite	0.676 ms	5 - 5 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.515 ms	0 - 111 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.741 ms	0 - 8 MB	NPU
MobileNet-v3-Small	ONNX	float	Qualcomm® QCS9075	1.014 ms	1 - 3 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.398 ms	0 - 101 MB	NPU
MobileNet-v3-Small	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.346 ms	0 - 100 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	0.556 ms	0 - 46 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.099 ms	1 - 31 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.828 ms	1 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA8775P	1.102 ms	1 - 32 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS9075	0.986 ms	3 - 5 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.601 ms	0 - 47 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA7255P	2.099 ms	1 - 31 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Qualcomm® SA8295P	1.464 ms	0 - 29 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.405 ms	1 - 31 MB	NPU
MobileNet-v3-Small	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.325 ms	1 - 34 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® X Elite	0.955 ms	0 - 0 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.544 ms	0 - 37 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS6490	2.28 ms	0 - 2 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	1.717 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.798 ms	0 - 15 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA8775P	0.994 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	2.799 ms	0 - 140 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.991 ms	0 - 39 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA7255P	1.717 ms	0 - 26 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Qualcomm® SA8295P	1.335 ms	0 - 23 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.375 ms	0 - 24 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.804 ms	0 - 25 MB	NPU
MobileNet-v3-Small	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.313 ms	0 - 28 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.557 ms	0 - 46 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.144 ms	0 - 31 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.84 ms	0 - 2 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8775P	1.145 ms	0 - 34 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS9075	1.011 ms	0 - 8 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.614 ms	0 - 48 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA7255P	2.144 ms	0 - 31 MB	NPU
MobileNet-v3-Small	TFLITE	float	Qualcomm® SA8295P	1.485 ms	0 - 30 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.435 ms	0 - 36 MB	NPU
MobileNet-v3-Small	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.331 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.