Image Classification
PyTorch
bu_auto
android

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:

  • 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® X2 Elite 1.333 ms 2 - 2 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.693 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.003 ms 0 - 129 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 1 Mobile 9.014 ms 1 - 132 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ IQ-8275 4.288 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.724 ms 0 - 72 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8450 9.014 ms 1 - 132 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 2.693 ms 57 - 57 MB NPU
ConvNext-Tiny ONNX float Qualcomm® Dragonwing™ Q-8750 1.548 ms 0 - 76 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Mobile 1.548 ms 0 - 76 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.298 ms 0 - 76 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 0.998 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.213 ms 29 - 29 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.548 ms 0 - 132 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 3.267 ms 0 - 130 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 9.583 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 2.196 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.168 ms 0 - 207 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8450 3.267 ms 0 - 130 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 2.374 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 2.213 ms 29 - 29 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 21.289 ms 0 - 239 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2.579 ms 0 - 117 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 1.143 ms 0 - 108 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Mobile 1.143 ms 0 - 108 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.942 ms 0 - 109 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2.579 ms 0 - 117 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X2 Elite 0.734 ms 1 - 1 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® X Elite 1.384 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.97 ms 0 - 115 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 2.157 ms 0 - 115 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.462 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.401 ms 0 - 4 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.394 ms 0 - 94 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® QCS8450 2.157 ms 0 - 115 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.512 ms 0 - 3 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.384 ms 30 - 30 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.682 ms 0 - 87 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.74 ms 0 - 84 MB NPU
ConvNext-Tiny ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.779 ms 0 - 80 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Mobile 0.779 ms 0 - 80 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.715 ms 0 - 87 MB NPU
ConvNext-Tiny ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.74 ms 0 - 84 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 2.022 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X Elite 3.636 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.484 ms 0 - 127 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Gen 1 Mobile 9.547 ms 0 - 130 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™ IQ-8275 14.807 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.432 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8775P 4.801 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8650P 4.801 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8255P 4.801 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 9.547 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.579 ms 3 - 5 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.636 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.951 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA7255P 14.807 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.754 ms 1 - 77 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Mobile 1.951 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.562 ms 1 - 78 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.649 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.367 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.174 ms 0 - 124 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 4.306 ms 0 - 124 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 11.706 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 3.012 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 6.848 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.1 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8775P 3.529 ms 0 - 97 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8650P 3.529 ms 0 - 97 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8255P 3.529 ms 0 - 97 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8450 4.306 ms 0 - 124 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 3.331 ms 2 - 4 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 3.367 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 22.364 ms 0 - 252 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 3.443 ms 0 - 110 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 1.585 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA7255P 6.848 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8295P 4.728 ms 0 - 94 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 1.585 ms 0 - 100 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.296 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.443 ms 0 - 110 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X2 Elite 0.934 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® X Elite 1.958 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.254 ms 0 - 105 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.617 ms 0 - 107 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.603 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.728 ms 0 - 3 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 3.776 ms 0 - 70 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.803 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8775P 2.049 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8650P 2.049 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8255P 2.049 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® QCS8450 2.617 ms 0 - 107 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.912 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.958 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 12.1 ms 0 - 96 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.137 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.965 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA7255P 3.776 ms 0 - 70 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Qualcomm® SA8295P 3.028 ms 0 - 67 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.965 ms 0 - 73 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.849 ms 0 - 81 MB NPU
ConvNext-Tiny QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.137 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.115 ms 0 - 128 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 1 Mobile 8.879 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.285 ms 0 - 60 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-8275 14.025 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.826 ms 0 - 3 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8775P 4.278 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 4.278 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 4.278 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 8.879 ms 0 - 123 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.052 ms 0 - 59 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® Dragonwing™ Q-8750 1.589 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA7255P 14.025 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.876 ms 0 - 65 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Mobile 1.589 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.336 ms 0 - 74 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.208 ms 0 - 111 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.693 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 41.816 ms 4 - 57 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.701 ms 0 - 32 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 3.742 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.739 ms 0 - 3 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8775P 2.02 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8650P 2.02 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8255P 2.02 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® QCS8450 2.693 ms 0 - 114 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.852 ms 0 - 31 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 27.208 ms 3 - 45 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 11.596 ms 3 - 45 MB CPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.916 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA7255P 3.742 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE w8a8 Qualcomm® SA8295P 2.973 ms 0 - 70 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.916 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.791 ms 0 - 84 MB NPU
ConvNext-Tiny TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 11.596 ms 3 - 45 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/ConvNext-Tiny