Hugging Face's logo

qualcomm
/
LeViT

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community

LeViT: Optimized for Qualcomm Devices

LeViT is a vision transformer model that can classify images from the Imagenet dataset.

This is based on the implementation of LeViT 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 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a16_mixed_int16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a16_mixed_int16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit LeViT 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 LeViT on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: LeViT-128S
  • Input resolution: 224x224
  • Number of parameters: 7.82M
  • Model size (float): 29.9 MB
  • Model size (w8a16): 8.83 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
LeViT ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.652 ms 1 - 77 MB NPU
LeViT ONNX float Snapdragon® 8 Elite Mobile 0.706 ms 0 - 76 MB NPU
LeViT ONNX float Snapdragon® X2 Elite 0.695 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.461 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.461 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 3 Mobile 0.869 ms 0 - 93 MB NPU
LeViT ONNX float Qualcomm® QCS8550 (Proxy) 1.259 ms 0 - 22 MB NPU
LeViT ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.706 ms 0 - 76 MB NPU
LeViT ONNX float Qualcomm® QCS9075 1.612 ms 1 - 3 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.466 ms 0 - 62 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Mobile 0.534 ms 0 - 53 MB NPU
LeViT ONNX w8a16 Snapdragon® X2 Elite 0.496 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.252 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.252 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.711 ms 0 - 80 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS6490 46.753 ms 12 - 16 MB CPU
LeViT ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.036 ms 0 - 23 MB NPU
LeViT ONNX w8a16 Qualcomm® QCM6690 18.621 ms 12 - 22 MB CPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 16.121 ms 13 - 23 MB CPU
LeViT ONNX w8a16 Qualcomm® QCS9075 1.27 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.534 ms 0 - 53 MB NPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 16.121 ms 13 - 23 MB CPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.484 ms 0 - 61 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.549 ms 0 - 59 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.511 ms 9 - 9 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.269 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.269 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.729 ms 0 - 86 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS6490 44.611 ms 11 - 16 MB CPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.064 ms 0 - 13 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.549 ms 0 - 59 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCM6690 18.861 ms 12 - 22 MB CPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 14.328 ms 12 - 23 MB CPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS9075 1.296 ms 0 - 3 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 14.328 ms 12 - 23 MB CPU
LeViT QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.717 ms 1 - 61 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Mobile 0.831 ms 0 - 62 MB NPU
LeViT QNN_DLC float Snapdragon® X2 Elite 0.937 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® X Elite 1.835 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® X Elite 1.835 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.068 ms 0 - 84 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.596 ms 1 - 2 MB NPU
LeViT QNN_DLC float Qualcomm® SA8775P 2.003 ms 1 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® SA8775P 2.003 ms 1 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® SA8775P 2.003 ms 1 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.373 ms 0 - 80 MB NPU
LeViT QNN_DLC float Qualcomm® SA7255P 3.788 ms 1 - 58 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.831 ms 0 - 62 MB NPU
LeViT QNN_DLC float Qualcomm® SA8295P 2.364 ms 0 - 52 MB NPU
LeViT QNN_DLC float Qualcomm® QCS9075 1.873 ms 1 - 3 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.583 ms 0 - 45 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.689 ms 0 - 40 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X2 Elite 0.802 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.64 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.64 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.963 ms 0 - 62 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.427 ms 0 - 2 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.724 ms 0 - 44 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.724 ms 0 - 44 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.724 ms 0 - 44 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCM6690 6.476 ms 0 - 165 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.472 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS9075 1.722 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA7255P 2.948 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.689 ms 0 - 40 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.472 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.602 ms 0 - 45 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.703 ms 0 - 39 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.788 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.657 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.657 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.982 ms 0 - 62 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.428 ms 0 - 46 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.739 ms 0 - 43 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.739 ms 0 - 43 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.739 ms 0 - 43 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.703 ms 0 - 39 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 6.701 ms 0 - 168 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 2.913 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.484 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 1.734 ms 0 - 2 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.484 ms 0 - 41 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.658 ms 0 - 68 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Mobile 0.782 ms 0 - 54 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 3 Mobile 1.033 ms 0 - 93 MB NPU
LeViT TFLITE float Qualcomm® QCS8550 (Proxy) 1.506 ms 0 - 2 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 2.0 ms 0 - 65 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 2.0 ms 0 - 65 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 2.0 ms 0 - 65 MB NPU
LeViT TFLITE float Qualcomm® QCS8450 (Proxy) 2.356 ms 0 - 79 MB NPU
LeViT TFLITE float Qualcomm® SA7255P 4.014 ms 0 - 62 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.782 ms 0 - 54 MB NPU
LeViT TFLITE float Qualcomm® SA8295P 2.339 ms 0 - 53 MB NPU
LeViT TFLITE float Qualcomm® QCS9075 1.861 ms 0 - 19 MB NPU

License

  • The license for the original implementation of LeViT 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/LeViT