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® 8 Elite Gen 5 Mobile	1.28 ms	1 - 126 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X2 Elite	1.341 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.922 ms	56 - 56 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.048 ms	0 - 170 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.703 ms	1 - 6 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS9075	3.943 ms	1 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.552 ms	0 - 120 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.102 ms	0 - 115 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X2 Elite	1.202 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.839 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.801 ms	0 - 141 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS6490	390.543 ms	49 - 64 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.506 ms	0 - 35 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS9075	2.663 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCM6690	209.445 ms	58 - 71 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.383 ms	0 - 108 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	200.929 ms	59 - 73 MB	CPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.633 ms	0 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X2 Elite	2.005 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.945 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.649 ms	0 - 173 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.242 ms	1 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.7 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	5.021 ms	1 - 126 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS9075	4.878 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.63 ms	0 - 168 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA7255P	15.242 ms	1 - 124 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8295P	8.975 ms	1 - 125 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.052 ms	1 - 129 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.281 ms	0 - 100 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.602 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X Elite	3.395 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.161 ms	0 - 121 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS6490	9.075 ms	2 - 4 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	6.84 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.115 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.503 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS9075	3.356 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCM6690	22.414 ms	0 - 250 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.246 ms	0 - 123 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA7255P	6.84 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8295P	4.74 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.611 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.486 ms	0 - 107 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.295 ms	0 - 126 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)	13.979 ms	0 - 121 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.84 ms	0 - 2 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.251 ms	0 - 123 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS9075	4.092 ms	0 - 59 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.905 ms	0 - 161 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA7255P	13.979 ms	0 - 121 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8295P	7.864 ms	0 - 118 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.591 ms	0 - 124 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.