You can deploy this model and start earning money today!

qualcomm/
ConvNext-Base

Name: ConvNext-Base
Rating: 2.5 (28 reviews)

Views

No views yet

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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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:

Input resolution: 224x224
Model checkpoint: Imagenet
Model size (float): 338 MB
Model size (w8a16): 88.7 MB
Number of parameters: 88.6M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ConvNext-Base	ONNX	float	Snapdragon® X2 Elite	3.533 ms	2 - 2 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X Elite	7.227 ms	176 - 176 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.353 ms	1 - 313 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 1 Mobile	19.291 ms	1 - 302 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	12.11 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.16 ms	0 - 194 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS8450	19.291 ms	1 - 302 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	10.743 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	7.227 ms	176 - 176 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ Q-8750	4.119 ms	0 - 185 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite Mobile	4.119 ms	0 - 185 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.203 ms	0 - 186 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X2 Elite	2.397 ms	1 - 1 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X Elite	4.99 ms	91 - 91 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.435 ms	0 - 261 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	7.969 ms	0 - 260 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	32.979 ms	0 - 3 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	4.902 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.86 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS8450	7.969 ms	0 - 260 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	4.884 ms	0 - 3 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	4.99 ms	91 - 91 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	58.22 ms	0 - 403 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	6.894 ms	0 - 259 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	2.78 ms	0 - 205 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.78 ms	0 - 205 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.163 ms	0 - 226 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6.894 ms	0 - 259 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X2 Elite	4.273 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X Elite	8.418 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	5.835 ms	0 - 304 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	20.406 ms	0 - 295 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	12.727 ms	1 - 4 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	41.907 ms	1 - 180 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.995 ms	1 - 2 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8775P	11.83 ms	1 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8650P	11.83 ms	1 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8255P	11.83 ms	1 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8450	20.406 ms	0 - 295 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	11.532 ms	3 - 5 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	8.418 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	4.532 ms	0 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA7255P	41.907 ms	1 - 180 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8295P	19.681 ms	1 - 171 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Mobile	4.532 ms	0 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.553 ms	1 - 187 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.15 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X Elite	6.281 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.086 ms	0 - 249 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	9.101 ms	0 - 251 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	29.644 ms	2 - 4 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	5.77 ms	0 - 3 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	14.633 ms	0 - 203 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.88 ms	0 - 27 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8775P	6.205 ms	0 - 205 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8650P	6.205 ms	0 - 205 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8255P	6.205 ms	0 - 205 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8450	9.101 ms	0 - 251 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	5.938 ms	2 - 4 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	6.281 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	60.894 ms	0 - 398 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	7.799 ms	0 - 256 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	3.256 ms	0 - 195 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA7255P	14.633 ms	0 - 203 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8295P	9.401 ms	0 - 204 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	3.256 ms	0 - 195 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.561 ms	0 - 214 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	7.799 ms	0 - 256 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.454 ms	0 - 302 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	19.686 ms	0 - 291 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	12.218 ms	0 - 178 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	40.991 ms	0 - 175 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.257 ms	0 - 2 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8775P	11.109 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8650P	11.109 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8255P	11.109 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8450	19.686 ms	0 - 291 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	11.124 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	4.105 ms	0 - 178 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA7255P	40.991 ms	0 - 175 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8295P	18.791 ms	0 - 160 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Mobile	4.105 ms	0 - 178 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.224 ms	0 - 182 MB	NPU

License

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

References

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.

qualcomm/ConvNext-Base