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 2.42, 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-Tiny 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-Tiny 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: 28.6M
• Model size (float): 109 MB
• Model size (w8a16): 28.9 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ConvNext-Tiny	ONNX	float	Snapdragon® X2 Elite	1.344 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.914 ms	56 - 56 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.034 ms	0 - 168 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.715 ms	1 - 106 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS9075	3.947 ms	0 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.554 ms	0 - 127 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.278 ms	0 - 127 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X2 Elite	1.47 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.819 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.798 ms	0 - 141 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS6490	369.385 ms	50 - 65 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.54 ms	0 - 38 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS9075	2.68 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCM6690	209.914 ms	60 - 74 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.403 ms	0 - 117 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	202.169 ms	59 - 73 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.089 ms	0 - 115 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X2 Elite	2.041 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.927 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.654 ms	0 - 171 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.256 ms	1 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.689 ms	1 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	5.004 ms	1 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS9075	4.876 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.683 ms	0 - 168 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA7255P	15.256 ms	1 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8295P	8.973 ms	1 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.027 ms	0 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.63 ms	1 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.614 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X Elite	3.409 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.19 ms	0 - 121 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS6490	9.06 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	6.854 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.12 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	15.078 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS9075	3.354 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCM6690	23.405 ms	0 - 250 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.273 ms	0 - 122 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA7255P	6.854 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8295P	4.736 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.614 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.484 ms	0 - 107 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.283 ms	0 - 100 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.124 ms	0 - 170 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8275 (Proxy)	13.958 ms	0 - 122 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.842 ms	0 - 2 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.265 ms	0 - 122 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS9075	4.078 ms	0 - 59 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.864 ms	0 - 163 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA7255P	13.958 ms	0 - 122 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8295P	7.882 ms	0 - 118 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.591 ms	0 - 126 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.299 ms	0 - 123 MB	NPU

License

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