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 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a16_mixed_int16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a16_mixed_int16 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 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 0.655 ms 1 - 77 MB NPU
LeViT ONNX float Snapdragon® X2 Elite 0.692 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.464 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 3 Mobile 0.861 ms 0 - 93 MB NPU
LeViT ONNX float Qualcomm® QCS8550 (Proxy) 1.252 ms 0 - 25 MB NPU
LeViT ONNX float Qualcomm® QCS9075 1.656 ms 1 - 3 MB NPU
LeViT ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.707 ms 0 - 67 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.469 ms 0 - 62 MB NPU
LeViT ONNX w8a16 Snapdragon® X2 Elite 0.5 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.239 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.713 ms 0 - 88 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS6490 46.135 ms 11 - 16 MB CPU
LeViT ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.039 ms 0 - 13 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS9075 1.262 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Qualcomm® QCM6690 18.543 ms 2 - 12 MB CPU
LeViT ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.538 ms 0 - 60 MB NPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 14.66 ms 11 - 20 MB CPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.485 ms 0 - 61 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.509 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.277 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.737 ms 0 - 84 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS6490 44.528 ms 11 - 17 MB CPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.063 ms 0 - 13 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCS9075 1.311 ms 0 - 3 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® QCM6690 18.63 ms 25 - 35 MB CPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.546 ms 0 - 59 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 15.893 ms 11 - 22 MB CPU
LeViT QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.743 ms 1 - 61 MB NPU
LeViT QNN_DLC float Snapdragon® X2 Elite 0.999 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® X Elite 1.802 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.082 ms 1 - 88 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8275 (Proxy) 3.843 ms 1 - 58 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.593 ms 1 - 47 MB NPU
LeViT QNN_DLC float Qualcomm® QCS9075 1.884 ms 1 - 3 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.363 ms 0 - 81 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.849 ms 1 - 59 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.633 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X2 Elite 0.851 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.669 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 1.017 ms 0 - 61 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.967 ms 0 - 40 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 1.46 ms 0 - 3 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS9075 1.724 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCM6690 5.673 ms 0 - 164 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.748 ms 0 - 42 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.473 ms 0 - 39 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.652 ms 0 - 41 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.858 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.703 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 1.037 ms 0 - 66 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 (Proxy) 3.052 ms 0 - 40 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 1.493 ms 0 - 12 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 1.745 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 6.08 ms 0 - 166 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.752 ms 0 - 37 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.506 ms 0 - 39 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.68 ms 0 - 72 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 3 Mobile 1.051 ms 0 - 90 MB NPU
LeViT TFLITE float Qualcomm® QCS8275 (Proxy) 4.099 ms 0 - 65 MB NPU
LeViT TFLITE float Qualcomm® QCS8550 (Proxy) 1.56 ms 0 - 2 MB NPU
LeViT TFLITE float Qualcomm® QCS9075 1.88 ms 0 - 19 MB NPU
LeViT TFLITE float Qualcomm® QCS8450 (Proxy) 2.399 ms 0 - 83 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.802 ms 0 - 72 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