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

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.50, ONNX Runtime 1.30.0	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit 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:

• Input resolution: 224x224
• Model checkpoint: Imagenet
• Model size (float): 8.45 MB
• Model size (w8a16): 2.79 MB
• Number of parameters: 2.21M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MNASNet05	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.224 ms	0 - 31 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.269 ms	0 - 32 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X2 Elite	0.253 ms	2 - 2 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X Elite	0.488 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.331 ms	0 - 50 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.793 ms	1 - 57 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	0.705 ms	0 - 4 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.501 ms	0 - 7 MB	NPU
MNASNet05	ONNX	float	Qualcomm® QCS8450	0.793 ms	1 - 57 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	0.704 ms	1 - 4 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.488 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.269 ms	0 - 32 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.226 ms	0 - 37 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.271 ms	0 - 36 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X2 Elite	0.243 ms	1 - 1 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X Elite	0.551 ms	0 - 0 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.366 ms	0 - 48 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	0.668 ms	0 - 53 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	1.724 ms	0 - 3 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	0.614 ms	0 - 4 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.545 ms	0 - 5 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® QCS8450	0.668 ms	0 - 53 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	0.668 ms	0 - 3 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	0.551 ms	0 - 0 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2.252 ms	0 - 142 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	0.56 ms	0 - 35 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	0.271 ms	0 - 36 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	0.56 ms	0 - 35 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.29 ms	1 - 32 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.392 ms	1 - 32 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® X2 Elite	0.416 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® X Elite	0.913 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.528 ms	0 - 48 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.528 ms	0 - 55 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	0.913 ms	1 - 4 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.782 ms	1 - 3 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS8450	1.528 ms	0 - 55 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	0.977 ms	1 - 3 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	0.913 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.392 ms	1 - 32 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA8295P	1.302 ms	0 - 31 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.312 ms	0 - 32 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.376 ms	0 - 33 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.417 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X Elite	0.947 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.553 ms	0 - 44 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	0.942 ms	0 - 46 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	2.237 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	0.814 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.798 ms	0 - 2 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8775P	0.986 ms	0 - 35 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8650P	0.986 ms	0 - 35 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8255P	0.986 ms	0 - 35 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS8450	0.942 ms	0 - 46 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	0.878 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	0.947 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	3.099 ms	0 - 137 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	0.818 ms	0 - 31 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	0.376 ms	0 - 33 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA7255P	1.72 ms	0 - 33 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8295P	1.198 ms	0 - 31 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.818 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.287 ms	0 - 33 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.389 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.519 ms	0 - 48 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.54 ms	0 - 56 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	0.921 ms	0 - 9 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.779 ms	0 - 2 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8775P	1.121 ms	0 - 35 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8650P	1.121 ms	0 - 35 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8255P	1.121 ms	0 - 35 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS8450	1.54 ms	0 - 56 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	0.991 ms	0 - 8 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.389 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8295P	1.297 ms	0 - 31 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.