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 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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	3.161 ms	1 - 285 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X2 Elite	3.536 ms	176 - 176 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X Elite	7.488 ms	175 - 175 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.314 ms	0 - 350 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.155 ms	0 - 195 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS9075	11.075 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.137 ms	0 - 283 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.589 ms	0 - 224 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X2 Elite	2.77 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X Elite	6.449 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	4.373 ms	0 - 269 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS6490	1091.433 ms	32 - 63 MB	CPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	6.193 ms	0 - 103 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS9075	5.896 ms	0 - 3 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCM6690	634.065 ms	43 - 57 MB	CPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.212 ms	0 - 210 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	607.014 ms	68 - 83 MB	CPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.542 ms	1 - 283 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X2 Elite	4.418 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X Elite	8.601 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	6.034 ms	0 - 349 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	42.216 ms	1 - 280 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	8.222 ms	1 - 3 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS9075	12.066 ms	1 - 3 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	20.621 ms	0 - 336 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	4.644 ms	1 - 281 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.522 ms	0 - 200 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.025 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X Elite	6.289 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.091 ms	0 - 248 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS6490	23.862 ms	2 - 4 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	14.601 ms	0 - 198 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	5.924 ms	0 - 3 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS9075	6.132 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCM6690	61.117 ms	0 - 394 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	8.985 ms	0 - 245 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.277 ms	0 - 189 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	7.775 ms	0 - 248 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.156 ms	0 - 278 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.442 ms	0 - 346 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8275 (Proxy)	40.92 ms	0 - 273 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8550 (Proxy)	7.243 ms	0 - 2 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS9075	11.514 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8450 (Proxy)	19.705 ms	0 - 331 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.13 ms	0 - 277 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.