Modelpublic

qualcomm/ConvNext-Tiny

sourceHugging Facebsd-3-clauseupdated 11d agoView on Hugging Face

1likes1.2kdownloads

Model Card

ConvNext-Tiny: Optimized for Qualcomm Devices

ConvNextTiny 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-Tiny 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
ONNX	w8a8	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
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit [ConvNext-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_tiny).

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-Tiny on GitHub for usage instructions.

Model Details

Model Type: Modelusecase.image_classification

Model Stats:

—Input resolution: 224x224
—Model checkpoint: Imagenet
—Model size (float): 109 MB
—Model size (w8a16): 28.9 MB
—Number of parameters: 28.6M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ConvNext-Tiny	ONNX	float	Snapdragon® X2 Elite	1.339 ms	2 - 2 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.685 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.02 ms	0 - 129 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 1 Mobile	9.022 ms	1 - 131 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	4.285 ms	0 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.717 ms	0 - 76 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS8450	9.022 ms	1 - 131 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	3.857 ms	1 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	2.685 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.551 ms	0 - 76 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite Mobile	1.551 ms	0 - 76 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.285 ms	0 - 77 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X2 Elite	1.034 ms	1 - 1 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.216 ms	30 - 30 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.522 ms	0 - 133 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	3.358 ms	0 - 131 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	9.819 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	2.196 ms	0 - 4 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.163 ms	0 - 35 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS8450	3.358 ms	0 - 131 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	2.373 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	2.216 ms	30 - 30 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	20.614 ms	0 - 239 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	2.586 ms	0 - 117 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.141 ms	0 - 107 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.141 ms	0 - 107 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.94 ms	0 - 108 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	2.586 ms	0 - 117 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® X2 Elite	0.629 ms	1 - 1 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® X Elite	1.375 ms	30 - 30 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.975 ms	0 - 115 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	2.176 ms	0 - 116 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	5.895 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.402 ms	0 - 4 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.386 ms	0 - 35 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® QCS8450	2.176 ms	0 - 116 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.509 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.375 ms	30 - 30 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	10.603 ms	0 - 87 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	1.739 ms	0 - 80 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.78 ms	0 - 80 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.78 ms	0 - 80 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.718 ms	0 - 87 MB	NPU
ConvNext-Tiny	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.739 ms	0 - 80 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X2 Elite	1.919 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.664 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.493 ms	0 - 128 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	9.498 ms	0 - 129 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	4.8 ms	1 - 4 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.425 ms	1 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	4.769 ms	1 - 78 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8650P	4.769 ms	1 - 78 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8255P	4.769 ms	1 - 78 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8450	9.498 ms	0 - 129 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	4.583 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	3.664 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.914 ms	1 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA7255P	14.82 ms	1 - 76 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8295P	8.758 ms	1 - 78 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.914 ms	1 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.577 ms	1 - 79 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.607 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X Elite	3.381 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.171 ms	0 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	4.264 ms	0 - 122 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	11.701 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.013 ms	0 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.114 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.508 ms	0 - 99 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8650P	3.508 ms	0 - 99 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8255P	3.508 ms	0 - 99 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8450	4.264 ms	0 - 122 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.33 ms	2 - 4 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.381 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	22.77 ms	0 - 251 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	3.417 ms	0 - 111 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	1.588 ms	0 - 102 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA7255P	6.848 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8295P	4.711 ms	0 - 94 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	1.588 ms	0 - 102 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.296 ms	0 - 101 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.417 ms	0 - 111 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.956 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® X Elite	1.93 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	1.25 ms	0 - 103 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	2.57 ms	0 - 105 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	6.652 ms	2 - 4 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.734 ms	0 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.791 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® SA8775P	2.066 ms	0 - 71 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® SA8650P	2.066 ms	0 - 71 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® SA8255P	2.066 ms	0 - 71 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® QCS8450	2.57 ms	0 - 105 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.905 ms	2 - 4 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.93 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	12.092 ms	0 - 91 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	2.135 ms	0 - 73 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.961 ms	0 - 72 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® SA7255P	3.811 ms	0 - 70 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Qualcomm® SA8295P	3.015 ms	0 - 67 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.961 ms	0 - 72 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.844 ms	0 - 79 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	2.135 ms	0 - 73 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.132 ms	0 - 127 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	8.871 ms	0 - 124 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	4.279 ms	0 - 60 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.824 ms	0 - 3 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.288 ms	0 - 75 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8650P	4.288 ms	0 - 75 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8255P	4.288 ms	0 - 75 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8450	8.871 ms	0 - 124 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	4.041 ms	0 - 59 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.588 ms	0 - 76 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA7255P	14.013 ms	0 - 73 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8295P	7.839 ms	0 - 72 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Mobile	1.588 ms	0 - 76 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.336 ms	0 - 75 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.203 ms	0 - 111 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	2.657 ms	0 - 111 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	32.548 ms	3 - 56 MB	CPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.687 ms	0 - 32 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.735 ms	0 - 3 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® SA8775P	2.01 ms	0 - 77 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® SA8650P	2.01 ms	0 - 77 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® SA8255P	2.01 ms	0 - 77 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® QCS8450	2.657 ms	0 - 111 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.855 ms	0 - 31 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	27.154 ms	4 - 47 MB	CPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	12.143 ms	4 - 46 MB	CPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.902 ms	0 - 71 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® SA7255P	3.766 ms	0 - 74 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Qualcomm® SA8295P	2.958 ms	0 - 70 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.902 ms	0 - 71 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.783 ms	0 - 82 MB	NPU
ConvNext-Tiny	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	12.143 ms	4 - 46 MB	CPU

License

—The license for the original implementation of ConvNext-Tiny 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.