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 2.42, ONNX Runtime 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.42, 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® 8 Elite Gen 5 Mobile 1.271 ms 1 - 125 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X2 Elite 1.345 ms 212 - 212 MB NPU
ConvNext-Tiny ONNX float Snapdragon® X Elite 2.687 ms 159 - 159 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Gen 3 Mobile 2.029 ms 1 - 169 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8550 (Proxy) 2.74 ms 0 - 79 MB NPU
ConvNext-Tiny ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.552 ms 0 - 125 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS9075 3.953 ms 1 - 46 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS8750 1.552 ms 0 - 125 MB NPU
ConvNext-Tiny ONNX float Qualcomm® QCS7181 2.687 ms 159 - 159 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.095 ms 0 - 117 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X2 Elite 1.208 ms 212 - 212 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® X Elite 2.612 ms 149 - 149 MB NPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.798 ms 0 - 141 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS6490 383.001 ms 49 - 63 MB CPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8550 (Proxy) 2.574 ms 0 - 60 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCM6690 205.946 ms 59 - 73 MB CPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 196.557 ms 60 - 74 MB CPU
ConvNext-Tiny ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.379 ms 0 - 118 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS9075 2.657 ms 0 - 45 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS7790 196.557 ms 60 - 74 MB CPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS8750 1.379 ms 0 - 118 MB NPU
ConvNext-Tiny ONNX w8a16 Qualcomm® QCS7181 2.612 ms 149 - 149 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.553 ms 1 - 80 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® X2 Elite 1.935 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 2.485 ms 0 - 128 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8275 14.818 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.477 ms 1 - 2 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8775P 4.771 ms 1 - 77 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8650P 4.771 ms 1 - 77 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8255P 4.771 ms 1 - 77 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8450 (Proxy) 9.486 ms 0 - 130 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA7255P 14.818 ms 1 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® SA8295P 8.749 ms 1 - 79 MB NPU
ConvNext-Tiny QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.929 ms 0 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS9075 4.64 ms 1 - 3 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS8750 1.929 ms 0 - 76 MB NPU
ConvNext-Tiny QNN_DLC float Qualcomm® QCS7181 3.636 ms 1 - 1 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.281 ms 0 - 102 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X2 Elite 1.585 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® X Elite 3.388 ms 0 - 0 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.15 ms 0 - 122 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8275 6.865 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.116 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8775P 3.53 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8650P 3.53 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA8255P 3.53 ms 0 - 99 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCM6690 22.912 ms 0 - 251 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® SA7255P 6.865 ms 0 - 98 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 3.409 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.583 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS9075 3.315 ms 0 - 2 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS7790 3.409 ms 0 - 111 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS8750 1.583 ms 0 - 101 MB NPU
ConvNext-Tiny QNN_DLC w8a16 Qualcomm® QCS7181 3.388 ms 0 - 0 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.304 ms 0 - 79 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Gen 3 Mobile 2.129 ms 0 - 126 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8275 14.019 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8550 (Proxy) 2.839 ms 0 - 2 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8775P 4.293 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8650P 4.293 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8255P 4.293 ms 0 - 75 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8450 (Proxy) 8.887 ms 0 - 124 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA7255P 14.019 ms 0 - 73 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® SA8295P 7.876 ms 0 - 72 MB NPU
ConvNext-Tiny TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.584 ms 0 - 77 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS9075 4.069 ms 0 - 59 MB NPU
ConvNext-Tiny TFLITE float Qualcomm® QCS8750 1.584 ms 0 - 77 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