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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a16_mixed_int16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8_mixed_int16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
LeViT ONNX float Snapdragon® X2 Elite 0.685 ms 2 - 2 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.316 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 3 Mobile 0.877 ms 0 - 85 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 1 Mobile 1.588 ms 1 - 85 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-8275 1.428 ms 1 - 4 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.272 ms 0 - 22 MB NPU
LeViT ONNX float Qualcomm® QCS8450 1.588 ms 1 - 85 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-9075 2.028 ms 1 - 3 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.316 ms 16 - 16 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ Q-8750 0.703 ms 0 - 61 MB NPU
LeViT ONNX float Snapdragon® 8 Elite Mobile 0.703 ms 0 - 61 MB NPU
LeViT ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.65 ms 0 - 60 MB NPU
LeViT ONNX w8a16 Snapdragon® X2 Elite 0.489 ms 1 - 1 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.067 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.691 ms 0 - 84 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.254 ms 0 - 83 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 4.261 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 1.041 ms 0 - 4 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.014 ms 0 - 12 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS8450 1.254 ms 0 - 83 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.171 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.067 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 4.332 ms 0 - 179 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.002 ms 0 - 55 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.518 ms 0 - 52 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Mobile 0.518 ms 0 - 52 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.474 ms 0 - 60 MB NPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.002 ms 0 - 55 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.509 ms 1 - 1 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® X Elite 1.114 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.721 ms 0 - 85 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.069 ms 0 - 58 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 1.217 ms 0 - 3 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 1.114 ms 10 - 10 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-8750 0.549 ms 0 - 55 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.549 ms 0 - 55 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.497 ms 0 - 63 MB NPU
LeViT ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 2.299 ms 0 - 75 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-8275 3.775 ms 7 - 10 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.015 ms 0 - 10 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 3.636 ms 7 - 9 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ Q-8750 1.629 ms 0 - 53 MB NPU
LeViT ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Mobile 1.629 ms 0 - 53 MB NPU
LeViT ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 1.382 ms 0 - 52 MB NPU
LeViT QNN_DLC float Snapdragon® X2 Elite 0.948 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® X Elite 1.819 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.081 ms 0 - 85 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.37 ms 0 - 81 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.657 ms 1 - 4 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.795 ms 1 - 58 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.592 ms 0 - 14 MB NPU
LeViT QNN_DLC float Qualcomm® SA8775P 1.992 ms 0 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® SA8650P 1.992 ms 0 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® SA8255P 1.992 ms 0 - 59 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8450 2.37 ms 0 - 81 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.828 ms 1 - 3 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.819 ms 1 - 1 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.832 ms 0 - 63 MB NPU
LeViT QNN_DLC float Qualcomm® SA7255P 3.795 ms 1 - 58 MB NPU
LeViT QNN_DLC float Qualcomm® SA8295P 2.372 ms 0 - 52 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Mobile 0.832 ms 0 - 63 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.723 ms 1 - 60 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X2 Elite 0.769 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.584 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.952 ms 0 - 69 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.345 ms 0 - 3 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 2.759 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.399 ms 0 - 2 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.686 ms 0 - 52 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8650P 1.686 ms 0 - 52 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8255P 1.686 ms 0 - 52 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.531 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.584 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 5.534 ms 0 - 174 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.416 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.657 ms 0 - 47 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA7255P 2.759 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.657 ms 0 - 47 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.568 ms 0 - 54 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.416 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.801 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.652 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.973 ms 0 - 75 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-8275 2.877 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.451 ms 0 - 3 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.759 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8650P 1.759 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8255P 1.759 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 1.665 ms 0 - 2 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 1.652 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-6690 5.938 ms 0 - 177 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-7790 1.435 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-8750 0.698 ms 0 - 49 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 2.877 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.698 ms 0 - 49 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.604 ms 0 - 57 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.435 ms 0 - 51 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 3 Mobile 1.028 ms 0 - 91 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 1 Mobile 2.358 ms 0 - 84 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.674 ms 0 - 20 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.004 ms 0 - 62 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.507 ms 1 - 24 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 1.979 ms 0 - 64 MB NPU
LeViT TFLITE float Qualcomm® SA8650P 1.979 ms 0 - 64 MB NPU
LeViT TFLITE float Qualcomm® SA8255P 1.979 ms 0 - 64 MB NPU
LeViT TFLITE float Qualcomm® QCS8450 2.358 ms 0 - 84 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.93 ms 0 - 19 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ Q-8750 0.781 ms 0 - 69 MB NPU
LeViT TFLITE float Qualcomm® SA7255P 4.004 ms 0 - 62 MB NPU
LeViT TFLITE float Qualcomm® SA8295P 2.353 ms 0 - 53 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Mobile 0.781 ms 0 - 69 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.66 ms 0 - 67 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