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 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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	1.278 ms	0 - 126 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite Mobile	1.567 ms	0 - 127 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X2 Elite	1.334 ms	57 - 57 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.899 ms	56 - 56 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® X Elite	2.899 ms	56 - 56 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.038 ms	0 - 169 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.748 ms	0 - 34 MB	NPU
ConvNext-Tiny	ONNX	float	Qualcomm® QCS9075	3.939 ms	0 - 4 MB	NPU
ConvNext-Tiny	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.567 ms	0 - 127 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.103 ms	0 - 115 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.386 ms	0 - 117 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X2 Elite	1.202 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.817 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® X Elite	2.817 ms	29 - 29 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.815 ms	0 - 141 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS6490	383.929 ms	50 - 64 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	2.523 ms	0 - 35 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCS9075	2.686 ms	0 - 3 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Qualcomm® QCM6690	208.813 ms	59 - 72 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.386 ms	0 - 117 MB	NPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	200.28 ms	59 - 73 MB	CPU
ConvNext-Tiny	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	200.28 ms	59 - 73 MB	CPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.545 ms	1 - 80 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.922 ms	0 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X2 Elite	1.94 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.684 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® X Elite	3.684 ms	1 - 1 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.485 ms	0 - 127 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	14.819 ms	1 - 76 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.48 ms	1 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	4.795 ms	1 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	4.795 ms	1 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8775P	4.795 ms	1 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS9075	4.644 ms	1 - 3 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.5 ms	0 - 128 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA7255P	14.819 ms	1 - 76 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Qualcomm® SA8295P	8.748 ms	1 - 78 MB	NPU
ConvNext-Tiny	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.922 ms	0 - 77 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.275 ms	0 - 102 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	1.588 ms	0 - 100 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.59 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X Elite	3.372 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® X Elite	3.372 ms	0 - 0 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.152 ms	0 - 121 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS6490	9.101 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	6.825 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.144 ms	0 - 101 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.517 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.517 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8775P	3.517 ms	0 - 97 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS9075	3.335 ms	0 - 2 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCM6690	21.788 ms	0 - 251 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.311 ms	0 - 121 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA7255P	6.825 ms	0 - 96 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Qualcomm® SA8295P	4.741 ms	0 - 93 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.588 ms	0 - 100 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.379 ms	0 - 110 MB	NPU
ConvNext-Tiny	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.379 ms	0 - 110 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.308 ms	0 - 77 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite Mobile	1.594 ms	0 - 78 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.13 ms	0 - 127 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8275 (Proxy)	14.014 ms	0 - 73 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.836 ms	0 - 8 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.269 ms	0 - 74 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.269 ms	0 - 74 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8775P	4.269 ms	0 - 74 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS9075	4.066 ms	0 - 59 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.891 ms	0 - 122 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA7255P	14.014 ms	0 - 73 MB	NPU
ConvNext-Tiny	TFLITE	float	Qualcomm® SA8295P	7.876 ms	0 - 71 MB	NPU
ConvNext-Tiny	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.594 ms	0 - 78 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.