MobileNet-v3-Large: Optimized for Qualcomm Devices

MobileNet-v3-Large 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-Large 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-Large 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-Large 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: 5.47M
Model size (float): 20.9 MB
Model size (w8a16): 6.35 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MobileNet-v3-Large	ONNX	float	Snapdragon® X2 Elite	0.361 ms	13 - 13 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® X Elite	0.853 ms	12 - 12 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.501 ms	0 - 54 MB	NPU
MobileNet-v3-Large	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.717 ms	1 - 2 MB	NPU
MobileNet-v3-Large	ONNX	float	Qualcomm® QCS9075	1.003 ms	1 - 3 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.398 ms	0 - 34 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.357 ms	0 - 39 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® X2 Elite	0.314 ms	6 - 6 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® X Elite	0.847 ms	6 - 6 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.47 ms	0 - 58 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS6490	55.177 ms	24 - 28 MB	CPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.681 ms	0 - 9 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS9075	0.861 ms	0 - 3 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCM6690	20.303 ms	25 - 33 MB	CPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.365 ms	0 - 35 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	14.391 ms	25 - 34 MB	CPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.29 ms	0 - 41 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® X2 Elite	0.56 ms	1 - 1 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® X Elite	1.212 ms	1 - 1 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.683 ms	0 - 54 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.974 ms	1 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.046 ms	1 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA8775P	5.911 ms	1 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS9075	1.23 ms	3 - 5 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.905 ms	0 - 58 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA7255P	2.974 ms	1 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA8295P	1.844 ms	0 - 34 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.525 ms	0 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.441 ms	1 - 40 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.513 ms	0 - 0 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® X Elite	1.122 ms	0 - 0 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.661 ms	0 - 48 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS6490	2.782 ms	2 - 4 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	2.088 ms	0 - 32 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.934 ms	0 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA8775P	1.169 ms	0 - 34 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS9075	1.142 ms	0 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCM6690	4.052 ms	0 - 146 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.225 ms	0 - 52 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA7255P	2.088 ms	0 - 32 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA8295P	1.625 ms	0 - 32 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.46 ms	0 - 31 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.991 ms	0 - 31 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.373 ms	0 - 35 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.711 ms	0 - 66 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS8275 (Proxy)	3.081 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.066 ms	0 - 88 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA8775P	1.411 ms	0 - 43 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS9075	1.278 ms	0 - 15 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.937 ms	0 - 65 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA7255P	3.081 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA8295P	1.887 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.535 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.446 ms	0 - 45 MB	NPU

License

The license for the original implementation of MobileNet-v3-Large 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/MobileNet-v3-Large

Searching for MobileNetV3

Paper • 1905.02244 • Published May 6, 2019