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 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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	1.268 ms	1 - 127 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X2 Elite	1.338 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.904 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.036 ms	0 - 172 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.701 ms	0 - 38 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS9075	3.946 ms	1 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.551 ms	0 - 122 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.083 ms	0 - 115 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X2 Elite	1.201 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.818 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.812 ms	0 - 142 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS6490	414.728 ms	49 - 64 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.525 ms	0 - 35 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS9075	2.668 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCM6690	208.185 ms	61 - 75 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.384 ms	0 - 109 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	200.224 ms	59 - 74 MB	CPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.63 ms	1 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X2 Elite	2.037 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.923 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.659 ms	0 - 170 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.685 ms	1 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	5.045 ms	1 - 126 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS9075	4.876 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.636 ms	0 - 169 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8295P	8.974 ms	1 - 125 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.031 ms	1 - 126 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.284 ms	0 - 100 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	3.4 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.201 ms	0 - 122 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS6490	9.081 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	6.881 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.115 ms	0 - 137 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.524 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS9075	3.361 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCM6690	21.836 ms	0 - 250 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.233 ms	0 - 121 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA7255P	6.881 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8295P	4.726 ms	0 - 93 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.605 ms	0 - 98 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.45 ms	0 - 107 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.303 ms	0 - 122 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.133 ms	0 - 169 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8275 (Proxy)	13.977 ms	0 - 121 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.843 ms	0 - 2 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.274 ms	0 - 123 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS9075	4.082 ms	0 - 59 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.889 ms	0 - 160 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA7255P	13.977 ms	0 - 121 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8295P	7.901 ms	0 - 119 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.588 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.