MNASNet05: Optimized for Qualcomm Devices

MNASNet05 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 MNASNet05 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

Download pre-exported model assets from MNASNet05 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 MNASNet05 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: 2.21M
• Model size (float): 8.45 MB
• Model size (w8a16): 2.79 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MNASNet05	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.217 ms	0 - 32 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X2 Elite	0.232 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X Elite	0.621 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.337 ms	0 - 47 MB	NPU
MNASNet05	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.488 ms	0 - 2 MB	NPU
MNASNet05	ONNX	float	Qualcomm® QCS9075	0.762 ms	1 - 3 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.28 ms	0 - 28 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.217 ms	0 - 32 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X2 Elite	0.216 ms	0 - 0 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X Elite	0.644 ms	2 - 2 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.344 ms	0 - 40 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® QCS6490	29.144 ms	10 - 13 MB	CPU
MNASNet05	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.519 ms	0 - 7 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® QCS9075	0.711 ms	0 - 3 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® QCM6690	10.406 ms	9 - 17 MB	CPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.261 ms	0 - 27 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	7.673 ms	10 - 18 MB	CPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.301 ms	1 - 33 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® X2 Elite	0.446 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® X Elite	0.989 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.522 ms	0 - 46 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	2.331 ms	1 - 29 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.821 ms	1 - 7 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA8775P	1.121 ms	1 - 31 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS9075	0.979 ms	3 - 5 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.573 ms	0 - 48 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA7255P	2.331 ms	1 - 29 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA8295P	1.443 ms	1 - 29 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.401 ms	0 - 34 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.296 ms	0 - 28 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.422 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X Elite	0.941 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.527 ms	0 - 36 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS6490	2.252 ms	0 - 2 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	1.675 ms	0 - 26 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.787 ms	0 - 2 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8775P	0.992 ms	0 - 27 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS9075	0.923 ms	0 - 2 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCM6690	3.035 ms	0 - 138 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.951 ms	0 - 38 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA7255P	1.675 ms	0 - 26 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8295P	1.247 ms	0 - 23 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.363 ms	0 - 25 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.795 ms	0 - 25 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.306 ms	0 - 34 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.531 ms	0 - 47 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS8275 (Proxy)	2.342 ms	0 - 30 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.801 ms	0 - 9 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8775P	4.757 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS9075	0.987 ms	0 - 8 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.587 ms	0 - 49 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA7255P	2.342 ms	0 - 30 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8295P	1.455 ms	0 - 29 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.398 ms	0 - 30 MB	NPU

License

• The license for the original implementation of MNASNet05 can be found here.

References

• MnasNet: Platform-Aware Neural Architecture Search for Mobile
• 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.