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 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 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 1.307 ms 0 - 83 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.563 ms 0 - 81 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X2 Elite 1.341 ms 2 - 2 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.655 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.015 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 1 Mobile 8.566 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-8275 4.28 ms 0 - 5 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.702 ms 1 - 3 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8450 8.566 ms 0 - 135 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-9075 3.854 ms 1 - 4 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.655 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ Q-8750 1.563 ms 0 - 81 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 1.086 ms 0 - 96 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 0.866 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.197 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.532 ms 0 - 137 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 2.951 ms 0 - 136 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 7.514 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 2.223 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.139 ms 0 - 7 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8450 2.951 ms 0 - 136 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 2.197 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 20.013 ms 0 - 224 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.623 ms 0 - 122 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 1.086 ms 0 - 96 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.623 ms 0 - 122 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.709 ms 0 - 93 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.777 ms 0 - 85 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X2 Elite 0.632 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X Elite 1.375 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.958 ms 0 - 119 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.894 ms 0 - 118 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.024 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.386 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.38 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® QCS8450 1.894 ms 0 - 118 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 1.375 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.764 ms 0 - 88 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.676 ms 0 - 84 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.777 ms 0 - 85 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.676 ms 0 - 84 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.598 ms 1 - 83 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.912 ms 1 - 81 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 1.958 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X Elite 3.639 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.483 ms 0 - 133 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 1 Mobile 8.62 ms 0 - 137 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.791 ms 1 - 4 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.421 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8650P 4.769 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8255P 4.769 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 8.62 ms 0 - 137 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.548 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.639 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.912 ms 1 - 81 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.581 ms 1 - 82 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.205 ms 0 - 86 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.512 ms 0 - 91 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.46 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.368 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.17 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 3.964 ms 0 - 129 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 9.378 ms 2 - 5 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 3.015 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.088 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 3.964 ms 0 - 129 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 3.318 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 3.368 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 21.332 ms 0 - 228 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 3.486 ms 0 - 115 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 1.512 ms 0 - 91 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8295P 4.591 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.486 ms 0 - 115 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.84 ms 0 - 80 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.965 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X2 Elite 0.952 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X Elite 1.954 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.232 ms 0 - 106 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.328 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.107 ms 2 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.736 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.8 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8650P 2.066 ms 0 - 71 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8255P 2.066 ms 0 - 71 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® QCS8450 2.328 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.906 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.954 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 12.26 ms 0 - 85 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.139 ms 0 - 76 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.965 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8295P 2.872 ms 0 - 72 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.139 ms 0 - 76 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.336 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.628 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.134 ms 0 - 137 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 1 Mobile 8.468 ms 0 - 132 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.334 ms 0 - 60 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.862 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 4.288 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 4.288 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 8.468 ms 0 - 132 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.048 ms 0 - 60 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ Q-8750 1.628 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.725 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.776 ms 0 - 84 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.907 ms 0 - 80 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.223 ms 0 - 116 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.357 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 33.647 ms 3 - 57 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.703 ms 0 - 32 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.726 ms 0 - 122 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8650P 2.01 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8255P 2.01 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® QCS8450 2.357 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.832 ms 0 - 32 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 27.602 ms 3 - 49 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 11.785 ms 3 - 49 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.907 ms 0 - 80 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA7255P 57.887 ms 1 - 27 MB GPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8295P 2.831 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 11.785 ms 3 - 49 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