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 2.50, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	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® 8 Elite Gen 5 For Galaxy Mobile	3.217 ms	0 - 188 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.139 ms	0 - 186 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® X2 Elite	3.573 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	5.356 ms	0 - 316 MB	NPU
ConvNext-Base	ONNX	float	Snapdragon® 8 Gen 1 Mobile	18.574 ms	1 - 308 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	12.176 ms	0 - 5 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.126 ms	0 - 194 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® QCS8450	18.574 ms	1 - 308 MB	NPU
ConvNext-Base	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	10.747 ms	1 - 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	4.139 ms	0 - 186 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.93 ms	0 - 207 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.566 ms	0 - 186 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X2 Elite	2.144 ms	1 - 1 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® X Elite	4.96 ms	91 - 91 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.422 ms	0 - 269 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	6.994 ms	0 - 265 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	20.07 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	4.866 ms	0 - 5 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.813 ms	0 - 98 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® QCS8450	6.994 ms	0 - 265 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	4.858 ms	0 - 4 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	4.96 ms	91 - 91 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	57.117 ms	0 - 375 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	6.892 ms	0 - 267 MB	NPU
ConvNext-Base	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	2.566 ms	0 - 186 MB	NPU
ConvNext-Base	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6.892 ms	0 - 267 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.537 ms	1 - 187 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	4.571 ms	1 - 182 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X2 Elite	4.329 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® X Elite	8.399 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	5.894 ms	0 - 310 MB	NPU
ConvNext-Base	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	19.03 ms	0 - 300 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	13.026 ms	1 - 4 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.955 ms	1 - 2 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8650P	11.824 ms	1 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8255P	11.824 ms	1 - 181 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® QCS8450	19.03 ms	0 - 300 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	11.513 ms	3 - 5 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	8.399 ms	1 - 1 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	4.571 ms	1 - 182 MB	NPU
ConvNext-Base	QNN_DLC	float	Qualcomm® SA8295P	19.476 ms	1 - 172 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.352 ms	0 - 198 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.051 ms	0 - 177 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.883 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® X Elite	6.223 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	4.052 ms	0 - 259 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	7.981 ms	0 - 259 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	22.168 ms	2 - 5 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	5.731 ms	0 - 4 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.823 ms	0 - 2 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8650P	6.189 ms	0 - 204 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8255P	6.189 ms	0 - 204 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® QCS8450	7.981 ms	0 - 259 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	5.898 ms	0 - 3 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	6.223 ms	0 - 0 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	69.886 ms	0 - 376 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	7.635 ms	0 - 262 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	3.051 ms	0 - 177 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Qualcomm® SA8295P	9.25 ms	0 - 216 MB	NPU
ConvNext-Base	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	7.635 ms	0 - 262 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.22 ms	0 - 184 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.136 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.416 ms	0 - 309 MB	NPU
ConvNext-Base	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	19.029 ms	0 - 297 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	12.423 ms	0 - 178 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.271 ms	0 - 215 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8650P	11.089 ms	0 - 176 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8255P	11.089 ms	0 - 176 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® QCS8450	19.029 ms	0 - 297 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	10.817 ms	0 - 178 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	4.136 ms	0 - 177 MB	NPU
ConvNext-Base	TFLITE	float	Qualcomm® SA8295P	18.464 ms	0 - 164 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.