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

  • Input resolution: 224x224
  • Model checkpoint: Imagenet
  • Model size (float): 338 MB
  • Model size (w8a16): 88.7 MB
  • Number of parameters: 88.6M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
ConvNext-Base ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.21 ms 1 - 189 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Elite For Galaxy Mobile 4.124 ms 0 - 187 MB NPU
ConvNext-Base ONNX float Snapdragon® X2 Elite 3.556 ms 2 - 2 MB NPU
ConvNext-Base ONNX float Snapdragon® X Elite 7.214 ms 176 - 176 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Gen 3 Mobile 5.364 ms 0 - 318 MB NPU
ConvNext-Base ONNX float Snapdragon® 8 Gen 1 Mobile 18.591 ms 0 - 307 MB NPU
ConvNext-Base ONNX float Qualcomm® Dragonwing™ IQ-8275 12.133 ms 0 - 5 MB NPU
ConvNext-Base ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.132 ms 0 - 194 MB NPU
ConvNext-Base ONNX float Qualcomm® QCS8450 18.591 ms 0 - 307 MB NPU
ConvNext-Base ONNX float Qualcomm® Dragonwing™ IQ-9075 11.083 ms 0 - 4 MB NPU
ConvNext-Base ONNX float Qualcomm® Dragonwing™ IQ-X7181 7.214 ms 176 - 176 MB NPU
ConvNext-Base ONNX float Qualcomm® Dragonwing™ Q-8750 4.124 ms 0 - 187 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.956 ms 0 - 209 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.586 ms 0 - 186 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® X2 Elite 2.145 ms 1 - 1 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® X Elite 4.934 ms 90 - 90 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.456 ms 0 - 268 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 6.992 ms 0 - 266 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 20.447 ms 0 - 4 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 4.878 ms 0 - 4 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.795 ms 0 - 98 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® QCS8450 6.992 ms 0 - 266 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 4.868 ms 0 - 4 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.934 ms 90 - 90 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 57.185 ms 0 - 378 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 6.858 ms 0 - 265 MB NPU
ConvNext-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.586 ms 0 - 186 MB NPU
ConvNext-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 6.858 ms 0 - 265 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.536 ms 1 - 186 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 4.527 ms 0 - 181 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® X2 Elite 4.342 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® X Elite 8.411 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.899 ms 0 - 312 MB NPU
ConvNext-Base QNN_DLC float Snapdragon® 8 Gen 1 Mobile 19.073 ms 0 - 300 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 12.784 ms 1 - 4 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.971 ms 1 - 2 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® SA8650P 11.824 ms 1 - 181 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® SA8255P 11.824 ms 1 - 181 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® QCS8450 19.073 ms 0 - 300 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 11.9 ms 3 - 5 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 8.411 ms 1 - 1 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® Dragonwing™ Q-8750 4.527 ms 0 - 181 MB NPU
ConvNext-Base QNN_DLC float Qualcomm® SA8295P 19.472 ms 1 - 173 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.35 ms 0 - 198 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 3.054 ms 0 - 178 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® X2 Elite 2.914 ms 0 - 0 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® X Elite 6.258 ms 0 - 0 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 4.075 ms 0 - 258 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 8.052 ms 0 - 258 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 22.454 ms 0 - 3 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 5.739 ms 0 - 4 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.826 ms 0 - 248 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® SA8650P 6.189 ms 0 - 204 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® SA8255P 6.189 ms 0 - 204 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® QCS8450 8.052 ms 0 - 258 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.91 ms 0 - 3 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.258 ms 0 - 0 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 71.564 ms 0 - 380 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 7.695 ms 0 - 263 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 3.054 ms 0 - 178 MB NPU
ConvNext-Base QNN_DLC w8a16 Qualcomm® SA8295P 9.247 ms 0 - 216 MB NPU
ConvNext-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 7.695 ms 0 - 263 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.22 ms 0 - 183 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 4.092 ms 0 - 172 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Gen 3 Mobile 5.414 ms 0 - 310 MB NPU
ConvNext-Base TFLITE float Snapdragon® 8 Gen 1 Mobile 18.912 ms 0 - 297 MB NPU
ConvNext-Base TFLITE float Qualcomm® Dragonwing™ IQ-8275 12.162 ms 0 - 178 MB NPU
ConvNext-Base TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.349 ms 0 - 2 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA8650P 11.089 ms 0 - 176 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA8255P 11.089 ms 0 - 176 MB NPU
ConvNext-Base TFLITE float Qualcomm® QCS8450 18.912 ms 0 - 297 MB NPU
ConvNext-Base TFLITE float Qualcomm® Dragonwing™ IQ-9075 10.93 ms 0 - 178 MB NPU
ConvNext-Base TFLITE float Qualcomm® Dragonwing™ Q-8750 4.092 ms 0 - 172 MB NPU
ConvNext-Base TFLITE float Qualcomm® SA8295P 18.463 ms 0 - 164 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/ConvNext-Base