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 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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	3.153 ms	0 - 285 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X2 Elite	3.532 ms	176 - 176 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X Elite	7.475 ms	175 - 175 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.302 ms	1 - 354 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.125 ms	0 - 195 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS9075	11.339 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.175 ms	0 - 286 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.59 ms	0 - 223 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X2 Elite	2.764 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X Elite	6.463 ms	90 - 90 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	4.39 ms	0 - 275 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS6490	1102.498 ms	33 - 63 MB	CPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	6.168 ms	0 - 103 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS9075	5.895 ms	0 - 3 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCM6690	626.463 ms	43 - 56 MB	CPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.193 ms	0 - 210 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	603.478 ms	48 - 63 MB	CPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.556 ms	0 - 283 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X2 Elite	4.3 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X Elite	8.598 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	6.011 ms	0 - 347 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	42.218 ms	1 - 280 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	8.238 ms	1 - 2 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS9075	12.273 ms	1 - 3 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	20.606 ms	0 - 337 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	4.671 ms	1 - 282 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.526 ms	0 - 200 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.044 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X Elite	6.269 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.095 ms	0 - 248 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS6490	23.68 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	5.926 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS9075	6.131 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCM6690	75.42 ms	0 - 395 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	9.35 ms	0 - 245 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.269 ms	0 - 190 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	7.776 ms	0 - 248 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.157 ms	0 - 278 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.447 ms	0 - 344 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8275 (Proxy)	40.936 ms	0 - 273 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8550 (Proxy)	7.265 ms	0 - 3 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS9075	11.184 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8450 (Proxy)	19.725 ms	0 - 333 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.106 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.