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 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	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	0.223 ms	0 - 32 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.265 ms	0 - 37 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X2 Elite	0.231 ms	2 - 2 MB	NPU
MNASNet05	ONNX	float	Snapdragon® X Elite	0.497 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.349 ms	0 - 50 MB	NPU
MNASNet05	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.793 ms	1 - 55 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	0.713 ms	0 - 4 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.486 ms	0 - 7 MB	NPU
MNASNet05	ONNX	float	Qualcomm® QCS8450	0.793 ms	1 - 55 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	0.703 ms	1 - 4 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.497 ms	5 - 5 MB	NPU
MNASNet05	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.265 ms	0 - 37 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.218 ms	0 - 35 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.259 ms	0 - 35 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X2 Elite	0.232 ms	1 - 1 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® X Elite	0.516 ms	0 - 0 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.345 ms	0 - 48 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	0.612 ms	0 - 52 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	1.666 ms	0 - 3 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	0.554 ms	0 - 4 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.513 ms	0 - 5 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® QCS8450	0.612 ms	0 - 52 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	0.654 ms	0 - 3 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	0.516 ms	0 - 0 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	2.24 ms	0 - 142 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	0.537 ms	0 - 35 MB	NPU
MNASNet05	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	0.259 ms	0 - 35 MB	NPU
MNASNet05	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	0.537 ms	0 - 35 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.289 ms	1 - 33 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	0.415 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® X Elite	0.935 ms	1 - 1 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.53 ms	0 - 48 MB	NPU
MNASNet05	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.528 ms	1 - 55 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	0.908 ms	1 - 4 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.783 ms	1 - 2 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA8650P	1.103 ms	1 - 30 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® SA8255P	1.103 ms	1 - 30 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® QCS8450	1.528 ms	1 - 55 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	0.972 ms	1 - 3 MB	NPU
MNASNet05	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	0.935 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	1.304 ms	0 - 31 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.301 ms	0 - 33 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.368 ms	0 - 37 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.395 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® X Elite	0.919 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.529 ms	0 - 44 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	0.865 ms	0 - 51 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	2.177 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	0.768 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.776 ms	0 - 2 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8775P	0.95 ms	0 - 34 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8650P	0.95 ms	0 - 34 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8255P	0.95 ms	0 - 34 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® QCS8450	0.865 ms	0 - 51 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	0.875 ms	0 - 3 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	0.919 ms	0 - 0 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	3.058 ms	0 - 137 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	0.79 ms	0 - 31 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	0.368 ms	0 - 37 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA7255P	1.641 ms	0 - 33 MB	NPU
MNASNet05	QNN_DLC	w8a16	Qualcomm® SA8295P	1.125 ms	0 - 30 MB	NPU
MNASNet05	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.79 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.289 ms	0 - 33 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.387 ms	0 - 36 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.517 ms	0 - 49 MB	NPU
MNASNet05	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.542 ms	0 - 56 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	0.926 ms	0 - 9 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.772 ms	0 - 2 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8650P	1.116 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA8255P	1.116 ms	0 - 31 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® QCS8450	1.542 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	0.387 ms	0 - 36 MB	NPU
MNASNet05	TFLITE	float	Qualcomm® SA7255P	3.354 ms	0 - 28 MB	GPU
MNASNet05	TFLITE	float	Qualcomm® SA8295P	1.301 ms	0 - 32 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.