ConvNext-Base: Optimized for Qualcomm Devices

ConvNextBase 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 ConvNext-Base 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	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit ConvNext-Base 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 ConvNext-Base 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: 88.6M
• Model size (float): 338 MB
• Model size (w8a16): 88.7 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.157 ms	1 - 285 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X2 Elite	3.529 ms	176 - 176 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X Elite	7.49 ms	175 - 175 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.307 ms	1 - 354 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.163 ms	0 - 197 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS9075	11.147 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.169 ms	0 - 285 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.605 ms	0 - 224 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X2 Elite	2.78 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X Elite	6.459 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	4.373 ms	0 - 272 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS6490	1081.835 ms	32 - 63 MB	CPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	6.206 ms	0 - 5 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS9075	5.894 ms	0 - 3 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCM6690	629.093 ms	69 - 84 MB	CPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.217 ms	0 - 210 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	601.029 ms	73 - 90 MB	CPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.534 ms	1 - 183 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X2 Elite	4.314 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X Elite	8.622 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	6.018 ms	0 - 306 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	42.42 ms	1 - 179 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	8.224 ms	1 - 460 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS9075	12.345 ms	1 - 3 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	20.612 ms	0 - 295 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	4.665 ms	0 - 182 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.52 ms	0 - 211 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.096 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X Elite	6.255 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.067 ms	0 - 247 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS6490	20.829 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	14.619 ms	0 - 201 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	5.897 ms	0 - 38 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS9075	6.119 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCM6690	75.647 ms	0 - 397 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	9.204 ms	0 - 250 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.279 ms	0 - 194 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	7.764 ms	0 - 253 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.158 ms	0 - 179 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.456 ms	0 - 303 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8275 (Proxy)	40.984 ms	0 - 175 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8550 (Proxy)	7.23 ms	0 - 2 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS9075	11.399 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8450 (Proxy)	19.692 ms	0 - 290 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.127 ms	0 - 179 MB	NPU

License

• The license for the original implementation of ConvNext-Base can be found here.

References

• A ConvNet for the 2020s
• 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.