Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community

ConvNext-Base: Optimized for Qualcomm Devices

ConvNextBase 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-Base 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-Base 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-Base 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: 88.6M
  • Model size (float): 338 MB
  • Model size (w8a16): 88.7 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
ConvNext-Base ONNX float Snapdragon® X2 Elite 3.5 ms 180 - 180 MB NPU
ConvNext-Base ONNX float Snapdragon® X Elite 7.219 ms 175 - 175 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Gen 3 Mobile 5.333 ms 1 - 301 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Gen 1 Mobile 19.237 ms 1 - 289 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS8550 (Proxy) 7.13 ms 0 - 195 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS8450 19.237 ms 1 - 289 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Elite Mobile 4.135 ms 0 - 182 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.143 ms 1 - 181 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS9075 10.986 ms 1 - 46 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS8750 4.135 ms 0 - 182 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS7181 7.219 ms 175 - 175 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® X2 Elite 2.388 ms 212 - 212 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® X Elite 4.977 ms 149 - 149 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.43 ms 0 - 253 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS8550 (Proxy) 4.864 ms 0 - 101 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS9075 5.0 ms 0 - 46 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.145 ms 0 - 223 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Elite Mobile 2.76 ms 0 - 208 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 6.88 ms 0 - 258 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCM6690 58.277 ms 0 - 400 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS7790 6.88 ms 0 - 258 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS8750 2.76 ms 0 - 208 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS7181 4.977 ms 149 - 149 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® X2 Elite 4.28 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® X Elite 8.399 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.855 ms 0 - 305 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Gen 1 Mobile 20.35 ms 0 - 296 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS8275 41.909 ms 1 - 180 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS8550 (Proxy) 7.971 ms 1 - 310 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS8450 20.35 ms 0 - 296 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Elite Mobile 4.571 ms 0 - 182 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® SA8295P 19.688 ms 1 - 171 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.497 ms 1 - 183 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® SA7255P 41.909 ms 1 - 180 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS9075 12.069 ms 1 - 3 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS8750 4.571 ms 0 - 182 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS7181 8.399 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® X2 Elite 3.124 ms 0 - 0 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® X Elite 6.31 ms 0 - 0 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 4.065 ms 0 - 250 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS8275 14.605 ms 0 - 203 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.935 ms 0 - 2 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS9075 6.12 ms 2 - 4 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.533 ms 0 - 217 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 3.273 ms 0 - 194 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 7.756 ms 0 - 254 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCM6690 74.969 ms 0 - 402 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® SA7255P 14.605 ms 0 - 203 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS7790 7.756 ms 0 - 254 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS8750 3.273 ms 0 - 194 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS7181 6.31 ms 0 - 0 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Gen 3 Mobile 5.471 ms 0 - 304 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Gen 1 Mobile 19.664 ms 0 - 290 MB NPU
ConvNext-Base TFLITE float Qualcomm® QCS8275 40.978 ms 0 - 175 MB NPU
ConvNext-Base TFLITE float Qualcomm® QCS8550 (Proxy) 7.284 ms 0 - 195 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA8775P 78.217 ms 0 - 27 MB GPU
ConvNext-Base TFLITE float Qualcomm® SA8650P 78.217 ms 0 - 27 MB GPU
ConvNext-Base TFLITE float Qualcomm® SA8255P 78.217 ms 0 - 27 MB GPU
ConvNext-Base TFLITE float Qualcomm® QCS8450 19.664 ms 0 - 290 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Elite Mobile 4.13 ms 0 - 178 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA8295P 18.782 ms 0 - 161 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.166 ms 0 - 183 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA7255P 40.978 ms 0 - 175 MB NPU
ConvNext-Base TFLITE float Qualcomm® QCS9075 11.379 ms 0 - 177 MB NPU
ConvNext-Base TFLITE float Qualcomm® QCS8750 4.13 ms 0 - 178 MB NPU

License

  • The license for the original implementation of ConvNext-Base 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-Base