---
library_name: pytorch
license: other
tags:
- backbone
- bu_auto
- android
pipeline_tag: image-classification

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/web-assets/model_demo.png)

# Swin-Tiny: Optimized for Qualcomm Devices

SwinTiny 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-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-w8a16.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-w8a16.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-tflite-float.zip)

For more device-specific assets and performance metrics, visit **[Swin-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_tiny)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) 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-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 28.8M
- Model size (float): 110 MB
- Model size (w8a16): 29.9 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.071 ms | 1 - 254 MB | NPU
| Swin-Tiny | ONNX | float | Snapdragon® X2 Elite | 4.398 ms | 61 - 61 MB | NPU
| Swin-Tiny | ONNX | float | Snapdragon® X Elite | 10.97 ms | 60 - 60 MB | NPU
| Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.896 ms | 0 - 315 MB | NPU
| Swin-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 10.279 ms | 0 - 74 MB | NPU
| Swin-Tiny | ONNX | float | Qualcomm® QCS9075 | 12.34 ms | 0 - 4 MB | NPU
| Swin-Tiny | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.027 ms | 1 - 216 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.432 ms | 0 - 248 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 3.678 ms | 33 - 33 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 8.831 ms | 34 - 34 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.445 ms | 0 - 348 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS6490 | 423.954 ms | 96 - 112 MB | CPU
| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.315 ms | 0 - 44 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 10.077 ms | 0 - 3 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 217.014 ms | 107 - 123 MB | CPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.357 ms | 0 - 289 MB | NPU
| Swin-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 199.597 ms | 107 - 124 MB | CPU
| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.849 ms | 0 - 424 MB | NPU
| Swin-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 4.433 ms | 1 - 1 MB | NPU
| Swin-Tiny | QNN_DLC | float | Snapdragon® X Elite | 10.433 ms | 1 - 1 MB | NPU
| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.278 ms | 0 - 594 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 22.039 ms | 1 - 440 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 9.571 ms | 1 - 2 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 10.93 ms | 1 - 182 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 11.969 ms | 1 - 3 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 15.33 ms | 0 - 244 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 22.039 ms | 1 - 440 MB | NPU
| Swin-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 14.292 ms | 1 - 435 MB | NPU
| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.777 ms | 1 - 418 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.829 ms | 0 - 441 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.423 ms | 0 - 0 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 10.929 ms | 0 - 0 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.536 ms | 0 - 509 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 17.481 ms | 0 - 438 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 9.967 ms | 0 - 190 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 10.561 ms | 0 - 446 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 11.794 ms | 0 - 2 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 40.36 ms | 0 - 519 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.481 ms | 0 - 438 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.944 ms | 0 - 436 MB | NPU
| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.679 ms | 0 - 427 MB | NPU
| Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.095 ms | 0 - 203 MB | NPU
| Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.861 ms | 0 - 281 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 23.322 ms | 0 - 209 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 10.613 ms | 0 - 3 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® SA8775P | 11.662 ms | 0 - 209 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® QCS9075 | 12.887 ms | 0 - 60 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 15.623 ms | 0 - 266 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® SA7255P | 23.322 ms | 0 - 209 MB | NPU
| Swin-Tiny | TFLITE | float | Qualcomm® SA8295P | 15.204 ms | 0 - 208 MB | NPU
| Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.146 ms | 0 - 199 MB | NPU

## License
* The license for the original implementation of Swin-Tiny can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).