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 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a16_mixed_int16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 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® X2 Elite 0.683 ms 2 - 2 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.33 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 3 Mobile 0.865 ms 0 - 84 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 1 Mobile 1.587 ms 1 - 84 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.276 ms 1 - 3 MB NPU
LeViT ONNX float Qualcomm® QCS8450 1.587 ms 1 - 84 MB NPU
LeViT ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.643 ms 0 - 59 MB NPU
LeViT ONNX float Snapdragon® 8 Elite Mobile 0.704 ms 0 - 55 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-9075 1.543 ms 1 - 3 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ Q-8750 0.704 ms 0 - 55 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.33 ms 16 - 16 MB NPU
LeViT ONNX w8a16 Snapdragon® X2 Elite 0.484 ms 1 - 1 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.058 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 1.236 ms 0 - 86 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 4.087 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.013 ms 0 - 11 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS8450 1.236 ms 0 - 86 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Mobile 0.519 ms 0 - 59 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.166 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.009 ms 0 - 57 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.468 ms 0 - 62 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 4.301 ms 0 - 179 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.009 ms 0 - 57 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.519 ms 0 - 59 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.058 ms 8 - 8 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 1.123 ms 11 - 11 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.735 ms 0 - 85 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.064 ms 0 - 3 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 1.205 ms 0 - 3 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.065 ms 0 - 59 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.499 ms 0 - 64 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-6690 4.736 ms 0 - 183 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.545 ms 0 - 56 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-7790 1.065 ms 0 - 59 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-8750 0.545 ms 0 - 56 MB NPU
LeViT ONNX w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 1.123 ms 11 - 11 MB NPU
LeViT QNN_DLC float Snapdragon® X2 Elite 0.96 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 1.069 ms 0 - 84 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.375 ms 0 - 81 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8275 3.775 ms 0 - 57 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.594 ms 1 - 2 MB NPU
LeViT QNN_DLC float Qualcomm® SA8775P 1.992 ms 1 - 60 MB NPU
LeViT QNN_DLC float Qualcomm® SA8650P 1.992 ms 1 - 60 MB NPU
LeViT QNN_DLC float Qualcomm® SA8255P 1.992 ms 1 - 60 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8450 2.375 ms 0 - 81 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.723 ms 1 - 63 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Mobile 0.829 ms 0 - 64 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.818 ms 1 - 3 MB NPU
LeViT QNN_DLC float Qualcomm® SA7255P 3.775 ms 0 - 57 MB NPU
LeViT QNN_DLC float Qualcomm® SA8295P 2.351 ms 0 - 52 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.829 ms 0 - 64 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.802 ms 1 - 1 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X2 Elite 0.783 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.591 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.932 ms 0 - 78 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® QCS8275 2.792 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.385 ms 0 - 13 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.69 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8650P 1.69 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8255P 1.69 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.659 ms 0 - 47 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.528 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA7255P 2.792 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.416 ms 0 - 50 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.567 ms 0 - 55 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 0.659 ms 0 - 47 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.591 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.841 ms 1 - 1 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.659 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.96 ms 0 - 72 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 2.912 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.46 ms 0 - 32 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8775P 1.766 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8650P 1.766 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA8255P 1.766 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 1.596 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 1.439 ms 0 - 52 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.612 ms 0 - 53 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-6690 5.592 ms 0 - 176 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.697 ms 0 - 49 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 2.912 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-7790 1.439 ms 0 - 52 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ Q-8750 0.697 ms 0 - 49 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 1.659 ms 0 - 0 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 3 Mobile 1.036 ms 0 - 91 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 1 Mobile 2.353 ms 0 - 84 MB NPU
LeViT TFLITE float Qualcomm® QCS8275 3.987 ms 0 - 62 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.501 ms 0 - 3 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 1.99 ms 0 - 63 MB NPU
LeViT TFLITE float Qualcomm® SA8650P 1.99 ms 0 - 63 MB NPU
LeViT TFLITE float Qualcomm® SA8255P 1.99 ms 0 - 63 MB NPU
LeViT TFLITE float Qualcomm® QCS8450 2.353 ms 0 - 84 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.658 ms 0 - 69 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Mobile 0.782 ms 0 - 69 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.81 ms 0 - 19 MB NPU
LeViT TFLITE float Qualcomm® SA7255P 3.987 ms 0 - 62 MB NPU
LeViT TFLITE float Qualcomm® SA8295P 2.341 ms 0 - 53 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ Q-8750 0.782 ms 0 - 69 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