ResNet18: Optimized for Qualcomm Devices

ResNet18 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 ResNet18 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	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	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 ResNet18 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 ResNet18 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: 11.7M
• Model size (float): 44.6 MB
• Model size (w8a8): 11.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet18	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.556 ms	1 - 26 MB	NPU
ResNet18	ONNX	float	Snapdragon® X2 Elite	0.58 ms	23 - 23 MB	NPU
ResNet18	ONNX	float	Snapdragon® X Elite	1.164 ms	22 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.772 ms	0 - 35 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.079 ms	0 - 26 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS9075	1.8 ms	1 - 3 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.626 ms	0 - 20 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.347 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X2 Elite	0.274 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X Elite	0.623 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.415 ms	0 - 48 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS6490	13.732 ms	6 - 20 MB	CPU
ResNet18	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.555 ms	0 - 2 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS9075	0.643 ms	0 - 3 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCM6690	11.375 ms	8 - 15 MB	CPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.361 ms	0 - 22 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	8.694 ms	7 - 15 MB	CPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.592 ms	1 - 27 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X2 Elite	0.659 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X Elite	1.45 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.909 ms	0 - 35 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.87 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.323 ms	1 - 2 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.946 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS9075	2.063 ms	1 - 3 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.436 ms	0 - 34 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA7255P	5.87 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8295P	2.308 ms	0 - 20 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.714 ms	1 - 28 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.276 ms	0 - 26 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.312 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X Elite	0.614 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.42 ms	0 - 47 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS6490	1.806 ms	2 - 4 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.331 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.534 ms	0 - 1 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.718 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS9075	0.617 ms	2 - 4 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCM6690	3.241 ms	0 - 32 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.742 ms	0 - 49 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA7255P	1.331 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8295P	0.952 ms	0 - 22 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.313 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.681 ms	0 - 31 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.585 ms	0 - 30 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.921 ms	0 - 55 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.814 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.322 ms	0 - 2 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.938 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS9075	2.04 ms	0 - 25 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.461 ms	0 - 55 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA7255P	5.814 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8295P	2.272 ms	0 - 22 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.711 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.228 ms	0 - 26 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.298 ms	0 - 48 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS6490	1.509 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.035 ms	0 - 23 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.38 ms	0 - 2 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	0.561 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS9075	0.473 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCM6690	2.808 ms	0 - 32 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.604 ms	0 - 48 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA7255P	1.035 ms	0 - 23 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8295P	0.76 ms	0 - 21 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.262 ms	0 - 27 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.546 ms	0 - 31 MB	NPU

License

• The license for the original implementation of ResNet18 can be found here.

References

• Deep Residual Learning for Image Recognition
• 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.