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 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.50, 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 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a16_mixed_int16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.50 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® 8 Elite Gen 5 For Galaxy Mobile 0.658 ms 0 - 61 MB NPU
LeViT ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.702 ms 0 - 64 MB NPU
LeViT ONNX float Snapdragon® X2 Elite 0.68 ms 2 - 2 MB NPU
LeViT ONNX float Snapdragon® X Elite 1.317 ms 16 - 16 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 3 Mobile 0.87 ms 0 - 91 MB NPU
LeViT ONNX float Snapdragon® 8 Gen 1 Mobile 1.482 ms 1 - 88 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-8275 1.387 ms 0 - 4 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.271 ms 0 - 22 MB NPU
LeViT ONNX float Qualcomm® QCS8450 1.482 ms 1 - 88 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-9075 1.484 ms 1 - 4 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.317 ms 16 - 16 MB NPU
LeViT ONNX float Qualcomm® Dragonwing™ Q-8750 0.702 ms 0 - 64 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.464 ms 0 - 62 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.515 ms 0 - 57 MB NPU
LeViT ONNX w8a16 Snapdragon® X2 Elite 0.478 ms 1 - 1 MB NPU
LeViT ONNX w8a16 Snapdragon® X Elite 1.052 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.695 ms 0 - 85 MB NPU
LeViT ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1.225 ms 0 - 89 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 3.313 ms 0 - 4 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 1.038 ms 0 - 4 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.012 ms 0 - 12 MB NPU
LeViT ONNX w8a16 Qualcomm® QCS8450 1.225 ms 0 - 89 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1.169 ms 0 - 3 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.052 ms 8 - 8 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 4.341 ms 0 - 176 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 1.003 ms 0 - 60 MB NPU
LeViT ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.515 ms 0 - 57 MB NPU
LeViT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1.003 ms 0 - 60 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.497 ms 0 - 63 MB NPU
LeViT ONNX w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.549 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 w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.55 ms 0 - 61 MB NPU
LeViT ONNX w8a8_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 2.211 ms 0 - 54 MB NPU
LeViT ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 2.433 ms 0 - 87 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-8275 4.178 ms 0 - 3 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.735 ms 0 - 3 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 3.898 ms 8 - 10 MB NPU
LeViT ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ Q-8750 2.211 ms 0 - 54 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.724 ms 1 - 62 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.834 ms 0 - 61 MB NPU
LeViT QNN_DLC float Snapdragon® X2 Elite 0.989 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® X Elite 1.774 ms 1 - 1 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.081 ms 0 - 87 MB NPU
LeViT QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.219 ms 0 - 86 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.616 ms 1 - 4 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.561 ms 1 - 2 MB NPU
LeViT QNN_DLC float Qualcomm® QCS8450 2.219 ms 0 - 86 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.774 ms 1 - 3 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.774 ms 1 - 1 MB NPU
LeViT QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.834 ms 0 - 61 MB NPU
LeViT QNN_DLC float Qualcomm® SA8295P 2.172 ms 0 - 57 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.585 ms 0 - 55 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.677 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X2 Elite 0.76 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® X Elite 1.59 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.949 ms 0 - 76 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 1.353 ms 0 - 3 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.38 ms 0 - 2 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8775P 1.701 ms 0 - 58 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8650P 1.701 ms 0 - 58 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA8255P 1.701 ms 0 - 58 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.556 ms 2 - 4 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.59 ms 0 - 0 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 5.542 ms 0 - 170 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.41 ms 0 - 56 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.677 ms 0 - 51 MB NPU
LeViT QNN_DLC w8a16 Qualcomm® SA7255P 2.771 ms 0 - 55 MB NPU
LeViT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.41 ms 0 - 56 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.604 ms 0 - 57 MB NPU
LeViT QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 0.698 ms 0 - 49 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™ 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® 7 Gen 4 Mobile 1.435 ms 0 - 51 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.614 ms 0 - 72 MB NPU
LeViT TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.724 ms 0 - 68 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 3 Mobile 0.95 ms 0 - 95 MB NPU
LeViT TFLITE float Snapdragon® 8 Gen 1 Mobile 2.055 ms 0 - 91 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.475 ms 0 - 20 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.375 ms 0 - 2 MB NPU
LeViT TFLITE float Qualcomm® SA8775P 8.097 ms 1 - 7 MB CPU
LeViT TFLITE float Qualcomm® SA8650P 8.097 ms 1 - 7 MB CPU
LeViT TFLITE float Qualcomm® SA8255P 8.097 ms 1 - 7 MB CPU
LeViT TFLITE float Qualcomm® QCS8450 2.055 ms 0 - 91 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.639 ms 0 - 19 MB NPU
LeViT TFLITE float Qualcomm® Dragonwing™ Q-8750 0.724 ms 0 - 68 MB NPU
LeViT TFLITE float Qualcomm® SA7255P 3.337 ms 0 - 63 MB NPU
LeViT TFLITE float Qualcomm® SA8295P 2.027 ms 0 - 57 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