Hugging Face's logo

qualcomm
/
ConvNext-Tiny

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community

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.

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 1.332 ms 2 - 2 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.697 ms 58 - 58 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.031 ms 0 - 128 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 1 Mobile 9.041 ms 1 - 129 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.723 ms 0 - 66 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8450 9.041 ms 1 - 129 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-9075 3.834 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.697 ms 58 - 58 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ Q-8750 1.547 ms 0 - 74 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Mobile 1.547 ms 0 - 74 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.299 ms 0 - 74 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 0.997 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.213 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.536 ms 0 - 137 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 3.292 ms 0 - 132 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 9.798 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.166 ms 0 - 196 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8450 3.292 ms 0 - 132 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 2.344 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 2.213 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 1.145 ms 0 - 110 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Mobile 1.145 ms 0 - 110 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.949 ms 0 - 109 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X2 Elite 0.632 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X Elite 1.369 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.975 ms 0 - 117 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 2.157 ms 0 - 116 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.875 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.383 ms 0 - 35 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® QCS8450 2.157 ms 0 - 116 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.501 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.369 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.777 ms 0 - 81 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Mobile 0.777 ms 0 - 81 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.708 ms 0 - 90 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 1.99 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X Elite 3.682 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.495 ms 0 - 127 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 1 Mobile 9.488 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ QCS8275 14.812 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.423 ms 0 - 32 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8775P 4.777 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8650P 4.777 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8255P 4.777 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 9.488 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 5.023 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.682 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.924 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA7255P 14.812 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.753 ms 1 - 79 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Mobile 1.924 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.554 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.587 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.352 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.167 ms 0 - 122 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 4.218 ms 0 - 123 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 11.625 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8275 6.854 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.095 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8775P 3.503 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8650P 3.503 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8255P 3.503 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8450 4.218 ms 0 - 123 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 3.312 ms 2 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 3.352 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 21.908 ms 0 - 250 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 3.453 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 1.582 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA7255P 6.854 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8295P 4.751 ms 0 - 94 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 1.582 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.298 ms 0 - 102 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.453 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X2 Elite 0.967 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X Elite 1.94 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.245 ms 0 - 104 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.588 ms 0 - 106 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.788 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8275 3.799 ms 0 - 70 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.796 ms 0 - 30 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8775P 2.066 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8650P 2.066 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8255P 2.066 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® QCS8450 2.588 ms 0 - 106 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.914 ms 2 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.94 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 12.059 ms 0 - 96 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.14 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.963 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA7255P 3.799 ms 0 - 70 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8295P 3.005 ms 0 - 67 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.963 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.846 ms 0 - 80 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.14 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.131 ms 0 - 125 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 1 Mobile 8.88 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ QCS8275 14.019 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.826 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8775P 4.265 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 4.265 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 4.265 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 8.88 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.045 ms 0 - 59 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ Q-8750 1.592 ms 0 - 72 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA7255P 14.019 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.858 ms 0 - 72 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Mobile 1.592 ms 0 - 72 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.327 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.229 ms 0 - 111 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.693 ms 0 - 113 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 38.74 ms 3 - 56 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS8275 3.793 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.726 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8775P 2.011 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8650P 2.011 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8255P 2.011 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® QCS8450 2.693 ms 0 - 113 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.931 ms 0 - 31 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 27.432 ms 3 - 45 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 11.808 ms 4 - 46 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.905 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA7255P 3.793 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8295P 2.962 ms 0 - 70 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.905 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.79 ms 0 - 84 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 11.808 ms 4 - 46 MB CPU

License

  • The license for the original implementation of ConvNext-Tiny can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/ConvNext-Tiny