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 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 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® X2 Elite 1.332 ms 212 - 212 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.702 ms 181 - 181 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.022 ms 1 - 118 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 1 Mobile 9.028 ms 1 - 119 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8550 (Proxy) 2.717 ms 0 - 72 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8450 9.028 ms 1 - 119 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Mobile 1.546 ms 0 - 73 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.273 ms 1 - 70 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS9075 3.926 ms 1 - 46 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8750 1.546 ms 0 - 73 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS7181 2.702 ms 181 - 181 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 0.999 ms 181 - 181 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.226 ms 149 - 149 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.539 ms 0 - 122 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8550 (Proxy) 2.161 ms 0 - 38 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS9075 2.314 ms 0 - 45 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.945 ms 0 - 105 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Mobile 1.145 ms 0 - 109 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.61 ms 0 - 113 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCM6690 20.984 ms 0 - 235 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS7790 2.61 ms 0 - 113 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8750 1.145 ms 0 - 109 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS7181 2.226 ms 149 - 149 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 1.997 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X Elite 3.709 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.482 ms 0 - 126 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 1 Mobile 9.495 ms 0 - 131 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8275 14.817 ms 1 - 75 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.419 ms 1 - 2 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 9.495 ms 0 - 131 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Mobile 1.936 ms 0 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.748 ms 1 - 79 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.564 ms 1 - 79 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA7255P 14.817 ms 1 - 75 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS9075 4.669 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8750 1.936 ms 0 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS7181 3.709 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.62 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.361 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.16 ms 0 - 124 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8275 6.846 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.111 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS9075 3.323 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.29 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 1.595 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.448 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCM6690 23.159 ms 0 - 251 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA7255P 6.846 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS7790 3.448 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8750 1.595 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS7181 3.361 ms 0 - 0 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.129 ms 0 - 127 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 1 Mobile 8.877 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8275 14.013 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8550 (Proxy) 2.824 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8775P 24.708 ms 0 - 27 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 24.708 ms 0 - 27 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 24.708 ms 0 - 27 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 8.877 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Mobile 1.59 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.854 ms 0 - 72 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.314 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA7255P 14.013 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS9075 4.059 ms 0 - 59 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8750 1.59 ms 0 - 76 MB NPU

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