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 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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® 8 Elite Gen 5 Mobile	0.357 ms	0 - 39 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® X2 Elite	0.341 ms	13 - 13 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® X Elite	0.86 ms	12 - 12 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.498 ms	0 - 53 MB	NPU
MobileNet-v3-Large	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.716 ms	1 - 3 MB	NPU
MobileNet-v3-Large	ONNX	float	Qualcomm® QCS9075	1.007 ms	1 - 3 MB	NPU
MobileNet-v3-Large	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.399 ms	0 - 34 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.29 ms	0 - 42 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® X2 Elite	0.324 ms	6 - 6 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® X Elite	0.835 ms	6 - 6 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.468 ms	0 - 57 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS6490	56.603 ms	23 - 27 MB	CPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.682 ms	0 - 9 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCS9075	0.842 ms	0 - 3 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Qualcomm® QCM6690	20.191 ms	24 - 33 MB	CPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.366 ms	0 - 42 MB	NPU
MobileNet-v3-Large	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	14.512 ms	31 - 40 MB	CPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.445 ms	1 - 40 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® X2 Elite	0.561 ms	1 - 1 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® X Elite	1.218 ms	1 - 1 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.689 ms	0 - 54 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.962 ms	1 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.049 ms	1 - 39 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA8775P	1.389 ms	1 - 38 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS9075	1.246 ms	1 - 3 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.918 ms	0 - 57 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA7255P	2.962 ms	1 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Qualcomm® SA8295P	1.857 ms	0 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.527 ms	1 - 36 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.363 ms	0 - 35 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.52 ms	0 - 0 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® X Elite	1.108 ms	0 - 0 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.663 ms	0 - 48 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS6490	2.81 ms	0 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	2.083 ms	0 - 32 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.935 ms	0 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA8775P	1.163 ms	0 - 34 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS9075	1.163 ms	0 - 2 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCM6690	4.025 ms	0 - 147 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.226 ms	0 - 51 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA7255P	2.083 ms	0 - 32 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Qualcomm® SA8295P	1.635 ms	0 - 31 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.457 ms	0 - 31 MB	NPU
MobileNet-v3-Large	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.989 ms	0 - 31 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.441 ms	0 - 45 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.707 ms	0 - 61 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)	1.061 ms	0 - 2 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA8775P	1.422 ms	0 - 43 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS9075	1.281 ms	0 - 15 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.945 ms	0 - 63 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA7255P	3.081 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Qualcomm® SA8295P	1.893 ms	0 - 40 MB	NPU
MobileNet-v3-Large	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.533 ms	0 - 40 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