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 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 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:

  • Input resolution: 224x224
  • Model checkpoint: Imagenet
  • Model size (float): 109 MB
  • Model size (w8a16): 28.9 MB
  • Number of parameters: 28.6M

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 For Galaxy Mobile 1.313 ms 0 - 80 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.56 ms 0 - 78 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X2 Elite 1.33 ms 2 - 2 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.664 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.026 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 1 Mobile 8.566 ms 0 - 136 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-8275 4.281 ms 0 - 5 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.693 ms 0 - 77 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8450 8.566 ms 0 - 136 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-9075 3.847 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.664 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ Q-8750 1.56 ms 0 - 78 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.87 ms 0 - 95 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.081 ms 0 - 96 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 0.867 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.191 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.538 ms 0 - 136 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 3.0 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 7.375 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 2.22 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.145 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8450 3.0 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 2.366 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 2.191 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 20.482 ms 0 - 223 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.678 ms 0 - 122 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 1.081 ms 0 - 96 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.678 ms 0 - 122 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.714 ms 0 - 91 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.775 ms 0 - 85 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X2 Elite 0.615 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X Elite 1.378 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.957 ms 0 - 121 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.903 ms 0 - 119 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.099 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.384 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.381 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® QCS8450 1.903 ms 0 - 119 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.504 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.378 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.817 ms 0 - 89 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.683 ms 0 - 84 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.775 ms 0 - 85 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.683 ms 0 - 84 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.596 ms 1 - 82 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.917 ms 0 - 82 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 1.953 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X Elite 3.686 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.477 ms 0 - 134 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 1 Mobile 8.609 ms 0 - 137 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.801 ms 1 - 4 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.449 ms 1 - 2 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 8.609 ms 0 - 137 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.543 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.686 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.917 ms 0 - 82 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.572 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.211 ms 0 - 86 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.508 ms 0 - 86 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.787 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.374 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.18 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 3.957 ms 0 - 128 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 9.594 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 3.018 ms 0 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.109 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8650P 3.508 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8255P 3.508 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8450 3.957 ms 0 - 128 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 3.352 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 3.374 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 22.352 ms 0 - 227 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 3.519 ms 0 - 115 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 1.508 ms 0 - 86 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8295P 4.615 ms 0 - 105 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.519 ms 0 - 115 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.85 ms 0 - 81 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.956 ms 0 - 77 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X2 Elite 0.932 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X Elite 1.937 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.228 ms 0 - 106 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.34 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.058 ms 2 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.72 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.796 ms 0 - 52 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8775P 2.016 ms 0 - 77 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8650P 2.016 ms 0 - 77 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8255P 2.016 ms 0 - 77 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® QCS8450 2.34 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.911 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.937 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 12.009 ms 0 - 85 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.142 ms 0 - 75 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.956 ms 0 - 77 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8295P 2.88 ms 0 - 72 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.142 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.338 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.612 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.133 ms 0 - 136 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 1 Mobile 8.461 ms 0 - 133 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.328 ms 0 - 60 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.864 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8775P 24.959 ms 0 - 25 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 24.959 ms 0 - 25 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 24.959 ms 0 - 25 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 8.461 ms 0 - 133 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.049 ms 0 - 60 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ Q-8750 1.612 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA7255P 57.246 ms 0 - 23 MB GPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.728 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.776 ms 0 - 83 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.9 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.186 ms 0 - 116 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.38 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 35.903 ms 4 - 58 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.701 ms 0 - 32 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.729 ms 0 - 53 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8775P 24.869 ms 1 - 28 MB GPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8650P 24.869 ms 1 - 28 MB GPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8255P 24.869 ms 1 - 28 MB GPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® QCS8450 2.38 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.814 ms 0 - 32 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 27.275 ms 2 - 48 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 11.747 ms 2 - 48 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.9 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA7255P 57.836 ms 1 - 27 MB GPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8295P 2.845 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 11.747 ms 2 - 48 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