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	0.553 ms	0 - 25 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite Mobile	0.632 ms	0 - 27 MB	NPU
ResNet18	ONNX	float	Snapdragon® X2 Elite	0.516 ms	23 - 23 MB	NPU
ResNet18	ONNX	float	Snapdragon® X Elite	1.164 ms	22 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® X Elite	1.164 ms	22 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.78 ms	0 - 35 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.062 ms	0 - 35 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS9075	1.795 ms	1 - 3 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.632 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.347 ms	0 - 26 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.354 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X2 Elite	0.278 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X Elite	0.622 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X Elite	0.622 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.424 ms	0 - 48 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS6490	13.676 ms	7 - 23 MB	CPU
ResNet18	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.557 ms	0 - 9 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS9075	0.643 ms	0 - 3 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCM6690	11.336 ms	6 - 13 MB	CPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.354 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	8.671 ms	6 - 13 MB	CPU
ResNet18	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	8.671 ms	6 - 13 MB	CPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.593 ms	1 - 27 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.71 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X2 Elite	0.658 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X Elite	1.446 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X Elite	1.446 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.924 ms	0 - 35 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.862 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.322 ms	1 - 2 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.943 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.943 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.943 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS9075	2.062 ms	3 - 5 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.444 ms	0 - 34 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA7255P	5.862 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8295P	2.311 ms	0 - 20 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.71 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.268 ms	0 - 26 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.309 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.292 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X Elite	0.613 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X Elite	0.613 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.399 ms	0 - 47 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS6490	1.804 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.328 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.544 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.711 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.711 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.711 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS9075	0.618 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCM6690	3.235 ms	0 - 32 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.741 ms	0 - 49 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA7255P	1.328 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8295P	0.937 ms	0 - 22 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.309 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.676 ms	0 - 31 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.676 ms	0 - 31 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.589 ms	0 - 30 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Mobile	0.704 ms	0 - 30 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.924 ms	0 - 56 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.853 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.32 ms	0 - 2 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.935 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.935 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.935 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS9075	2.043 ms	0 - 25 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.467 ms	0 - 60 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA7255P	5.853 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8295P	2.281 ms	0 - 22 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.704 ms	0 - 30 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.228 ms	0 - 26 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.248 ms	0 - 27 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.295 ms	0 - 48 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS6490	1.467 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.019 ms	0 - 24 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.385 ms	0 - 80 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	0.555 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	0.555 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	0.555 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS9075	0.473 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCM6690	2.799 ms	0 - 32 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.609 ms	0 - 47 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA7255P	1.019 ms	0 - 24 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8295P	0.748 ms	0 - 22 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.248 ms	0 - 27 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.548 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.548 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.