Hugging Face's logo

qualcomm
/
Swin-Base

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community

Swin-Base: Optimized for Qualcomm Devices

SwinBase 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 Swin-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 Swin-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 Swin-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): 339 MB
  • Model size (w8a16): 90.2 MB
  • Number of parameters: 88.8M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Swin-Base ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 7.624 ms 0 - 388 MB NPU
Swin-Base ONNX float Snapdragon® 8 Elite For Galaxy Mobile 9.433 ms 1 - 371 MB NPU
Swin-Base ONNX float Snapdragon® X2 Elite 7.812 ms 2 - 2 MB NPU
Swin-Base ONNX float Snapdragon® X Elite 19.095 ms 175 - 175 MB NPU
Swin-Base ONNX float Snapdragon® 8 Gen 3 Mobile 12.56 ms 0 - 528 MB NPU
Swin-Base ONNX float Snapdragon® 8 Gen 1 Mobile 28.179 ms 1 - 520 MB NPU
Swin-Base ONNX float Qualcomm® Dragonwing™ IQ-8275 20.457 ms 0 - 5 MB NPU
Swin-Base ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 18.522 ms 0 - 194 MB NPU
Swin-Base ONNX float Qualcomm® QCS8450 28.179 ms 1 - 520 MB NPU
Swin-Base ONNX float Qualcomm® Dragonwing™ IQ-9075 21.987 ms 0 - 4 MB NPU
Swin-Base ONNX float Qualcomm® Dragonwing™ IQ-X7181 19.095 ms 175 - 175 MB NPU
Swin-Base ONNX float Qualcomm® Dragonwing™ Q-8750 9.433 ms 1 - 371 MB NPU
Swin-Base ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 6.143 ms 0 - 414 MB NPU
Swin-Base ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 7.966 ms 0 - 399 MB NPU
Swin-Base ONNX w8a16 Snapdragon® X2 Elite 6.313 ms 1 - 1 MB NPU
Swin-Base ONNX w8a16 Snapdragon® X Elite 16.391 ms 93 - 93 MB NPU
Swin-Base ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 10.723 ms 0 - 538 MB NPU
Swin-Base ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 20.247 ms 0 - 537 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 39.041 ms 0 - 4 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 14.394 ms 0 - 4 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 15.89 ms 0 - 518 MB NPU
Swin-Base ONNX w8a16 Qualcomm® QCS8450 20.247 ms 0 - 537 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 16.163 ms 0 - 4 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 16.391 ms 93 - 93 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 108.62 ms 0 - 667 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 17.916 ms 0 - 613 MB NPU
Swin-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 7.966 ms 0 - 399 MB NPU
Swin-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 17.916 ms 0 - 613 MB NPU
Swin-Base QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 7.17 ms 0 - 370 MB NPU
Swin-Base QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 8.965 ms 1 - 353 MB NPU
Swin-Base QNN_DLC float Snapdragon® X2 Elite 7.868 ms 1 - 1 MB NPU
Swin-Base QNN_DLC float Snapdragon® X Elite 18.641 ms 1 - 1 MB NPU
Swin-Base QNN_DLC float Snapdragon® 8 Gen 3 Mobile 12.199 ms 1 - 507 MB NPU
Swin-Base QNN_DLC float Snapdragon® 8 Gen 1 Mobile 27.857 ms 0 - 492 MB NPU
Swin-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 19.82 ms 1 - 4 MB NPU
Swin-Base QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 17.928 ms 1 - 322 MB NPU
Swin-Base QNN_DLC float Qualcomm® SA8775P 20.855 ms 1 - 351 MB NPU
Swin-Base QNN_DLC float Qualcomm® SA8650P 20.855 ms 1 - 351 MB NPU
Swin-Base QNN_DLC float Qualcomm® SA8255P 20.855 ms 1 - 351 MB NPU
Swin-Base QNN_DLC float Qualcomm® QCS8450 27.857 ms 0 - 492 MB NPU
Swin-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 21.148 ms 3 - 5 MB NPU
Swin-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 18.641 ms 1 - 1 MB NPU
Swin-Base QNN_DLC float Qualcomm® Dragonwing™ Q-8750 8.965 ms 1 - 353 MB NPU
Swin-Base QNN_DLC float Qualcomm® SA8295P 27.016 ms 1 - 343 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 7.138 ms 0 - 401 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 9.3 ms 0 - 388 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® X2 Elite 7.645 ms 0 - 0 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® X Elite 20.238 ms 0 - 0 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 12.963 ms 0 - 512 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 17.063 ms 0 - 4 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 19.506 ms 0 - 2 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® SA8650P 19.574 ms 0 - 411 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® SA8255P 19.574 ms 0 - 411 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 19.858 ms 2 - 5 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 20.238 ms 0 - 0 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 94.703 ms 0 - 645 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 21.623 ms 0 - 589 MB NPU
Swin-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 9.3 ms 0 - 388 MB NPU
Swin-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 21.623 ms 0 - 589 MB NPU
Swin-Base TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 7.727 ms 0 - 379 MB NPU
Swin-Base TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 9.501 ms 0 - 358 MB NPU
Swin-Base TFLITE float Snapdragon® 8 Gen 3 Mobile 12.818 ms 0 - 504 MB NPU
Swin-Base TFLITE float Snapdragon® 8 Gen 1 Mobile 27.835 ms 0 - 497 MB NPU
Swin-Base TFLITE float Qualcomm® Dragonwing™ IQ-8275 20.137 ms 0 - 179 MB NPU
Swin-Base TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 18.637 ms 0 - 4 MB NPU
Swin-Base TFLITE float Qualcomm® SA8775P 21.613 ms 0 - 359 MB NPU
Swin-Base TFLITE float Qualcomm® SA8650P 21.613 ms 0 - 359 MB NPU
Swin-Base TFLITE float Qualcomm® SA8255P 21.613 ms 0 - 359 MB NPU
Swin-Base TFLITE float Qualcomm® QCS8450 27.835 ms 0 - 497 MB NPU
Swin-Base TFLITE float Qualcomm® Dragonwing™ IQ-9075 21.746 ms 0 - 178 MB NPU
Swin-Base TFLITE float Qualcomm® Dragonwing™ Q-8750 9.501 ms 0 - 358 MB NPU
Swin-Base TFLITE float Qualcomm® SA7255P 52.046 ms 0 - 367 MB NPU
Swin-Base TFLITE float Qualcomm® SA8295P 27.746 ms 0 - 351 MB NPU

License

  • The license for the original implementation of Swin-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/Swin-Base