MobileNet-v2: Optimized for Qualcomm Devices

MobileNetV2 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-v2 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
ONNX	w8a16_mixed_int16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16_mixed_int16	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit MobileNet-v2 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-v2 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: 3.49M
• Model size (float): 13.3 MB
• Model size (w8a16): 4.39 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MobileNet-v2	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.277 ms	0 - 33 MB	NPU
MobileNet-v2	ONNX	float	Snapdragon® X2 Elite	0.306 ms	7 - 7 MB	NPU
MobileNet-v2	ONNX	float	Snapdragon® X Elite	0.778 ms	7 - 7 MB	NPU
MobileNet-v2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.42 ms	0 - 52 MB	NPU
MobileNet-v2	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.63 ms	0 - 2 MB	NPU
MobileNet-v2	ONNX	float	Qualcomm® QCS9075	0.904 ms	1 - 3 MB	NPU
MobileNet-v2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.336 ms	0 - 35 MB	NPU
MobileNet-v2	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.236 ms	0 - 36 MB	NPU
MobileNet-v2	ONNX	w8a16	Snapdragon® X2 Elite	0.278 ms	5 - 5 MB	NPU
MobileNet-v2	ONNX	w8a16	Snapdragon® X Elite	0.706 ms	3 - 3 MB	NPU
MobileNet-v2	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.409 ms	0 - 46 MB	NPU
MobileNet-v2	ONNX	w8a16	Qualcomm® QCS6490	47.245 ms	15 - 18 MB	CPU
MobileNet-v2	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.579 ms	0 - 24 MB	NPU
MobileNet-v2	ONNX	w8a16	Qualcomm® QCS9075	0.775 ms	0 - 3 MB	NPU
MobileNet-v2	ONNX	w8a16	Qualcomm® QCM6690	17.867 ms	14 - 22 MB	CPU
MobileNet-v2	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.293 ms	0 - 30 MB	NPU
MobileNet-v2	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	13.1 ms	15 - 23 MB	CPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	0.257 ms	0 - 37 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® X2 Elite	0.33 ms	6 - 6 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® X Elite	0.755 ms	4 - 4 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® 8 Gen 3 Mobile	0.461 ms	0 - 47 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Qualcomm® QCS6490	47.379 ms	15 - 18 MB	CPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Qualcomm® QCS8550 (Proxy)	0.641 ms	0 - 30 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Qualcomm® QCS9075	0.822 ms	0 - 3 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Qualcomm® QCM6690	18.294 ms	14 - 21 MB	CPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® 8 Elite For Galaxy Mobile	0.339 ms	0 - 32 MB	NPU
MobileNet-v2	ONNX	w8a16_mixed_int16	Snapdragon® 7 Gen 4 Mobile	13.103 ms	15 - 23 MB	CPU
MobileNet-v2	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.253 ms	0 - 35 MB	NPU
MobileNet-v2	ONNX	w8a8	Snapdragon® X2 Elite	0.279 ms	5 - 5 MB	NPU
MobileNet-v2	ONNX	w8a8	Snapdragon® X Elite	0.595 ms	3 - 3 MB	NPU
MobileNet-v2	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.338 ms	0 - 46 MB	NPU
MobileNet-v2	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.484 ms	0 - 2 MB	NPU
MobileNet-v2	ONNX	w8a8	Qualcomm® QCS9075	0.645 ms	0 - 3 MB	NPU
MobileNet-v2	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.303 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.344 ms	1 - 34 MB	NPU
MobileNet-v2	QNN_DLC	float	Snapdragon® X2 Elite	0.487 ms	1 - 1 MB	NPU
MobileNet-v2	QNN_DLC	float	Snapdragon® X Elite	1.081 ms	1 - 1 MB	NPU
MobileNet-v2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.601 ms	0 - 49 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.656 ms	1 - 30 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.923 ms	1 - 2 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® SA8775P	1.196 ms	1 - 31 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® QCS9075	1.124 ms	1 - 3 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.702 ms	0 - 52 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® SA7255P	2.656 ms	1 - 30 MB	NPU
MobileNet-v2	QNN_DLC	float	Qualcomm® SA8295P	1.504 ms	0 - 28 MB	NPU
MobileNet-v2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.448 ms	0 - 33 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.296 ms	0 - 33 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.436 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® X Elite	0.949 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.561 ms	0 - 41 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCS6490	2.292 ms	0 - 2 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	1.755 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.802 ms	0 - 20 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® SA8775P	1.012 ms	0 - 31 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCS9075	1.007 ms	0 - 2 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCM6690	3.344 ms	0 - 143 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.979 ms	0 - 44 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® SA7255P	1.755 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Qualcomm® SA8295P	1.285 ms	0 - 28 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.374 ms	0 - 34 MB	NPU
MobileNet-v2	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.864 ms	0 - 141 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	0.321 ms	0 - 33 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® X2 Elite	0.469 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® X Elite	1.01 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® 8 Gen 3 Mobile	0.587 ms	0 - 42 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® QCS8275 (Proxy)	1.988 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® QCS8550 (Proxy)	0.86 ms	0 - 24 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® SA8775P	1.051 ms	0 - 32 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® QCS9075	1.024 ms	0 - 2 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® QCM6690	4.741 ms	0 - 144 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Qualcomm® SA7255P	1.988 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® 8 Elite For Galaxy Mobile	0.411 ms	0 - 30 MB	NPU
MobileNet-v2	QNN_DLC	w8a16_mixed_int16	Snapdragon® 7 Gen 4 Mobile	0.975 ms	0 - 142 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.184 ms	0 - 33 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.284 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® X Elite	0.577 ms	0 - 0 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.308 ms	0 - 42 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCS6490	1.293 ms	0 - 2 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.077 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.459 ms	0 - 1 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® SA8775P	0.625 ms	0 - 31 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCS9075	0.547 ms	0 - 2 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCM6690	1.79 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.629 ms	0 - 43 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® SA7255P	1.077 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Qualcomm® SA8295P	0.821 ms	0 - 27 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.224 ms	0 - 29 MB	NPU
MobileNet-v2	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.479 ms	0 - 29 MB	NPU
MobileNet-v2	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.341 ms	0 - 37 MB	NPU
MobileNet-v2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.594 ms	0 - 53 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.7 ms	0 - 33 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.927 ms	0 - 3 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® SA8775P	1.224 ms	0 - 35 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® QCS9075	1.127 ms	0 - 10 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.714 ms	0 - 55 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® SA7255P	2.7 ms	0 - 33 MB	NPU
MobileNet-v2	TFLITE	float	Qualcomm® SA8295P	1.505 ms	0 - 30 MB	NPU
MobileNet-v2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.45 ms	0 - 33 MB	NPU
MobileNet-v2	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.182 ms	0 - 36 MB	NPU
MobileNet-v2	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.289 ms	0 - 43 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCS6490	1.248 ms	0 - 7 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.0 ms	0 - 32 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.413 ms	0 - 2 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® SA8775P	0.596 ms	0 - 33 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCS9075	0.552 ms	0 - 6 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCM6690	1.641 ms	0 - 29 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.544 ms	0 - 46 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® SA7255P	1.0 ms	0 - 32 MB	NPU
MobileNet-v2	TFLITE	w8a8	Qualcomm® SA8295P	0.823 ms	0 - 29 MB	NPU
MobileNet-v2	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.216 ms	0 - 30 MB	NPU
MobileNet-v2	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.414 ms	0 - 30 MB	NPU

License

• The license for the original implementation of MobileNet-v2 can be found here.

References

• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• 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.