Hugging Face's logo

qualcomm
/
Mobile-VIT

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community

Mobile-VIT: Optimized for Qualcomm Devices

MobileVit is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of Mobile-VIT 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
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download

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

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Input resolution: 224x224
  • Model checkpoint: Imagenet
  • Model size (float): 21.4 MB
  • Model size (w8a16): 6.56 MB
  • Number of parameters: 5.57M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Mobile-VIT ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.925 ms 0 - 65 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.294 ms 0 - 65 MB NPU
Mobile-VIT ONNX float Snapdragon® X2 Elite 2.128 ms 2 - 2 MB NPU
Mobile-VIT ONNX float Snapdragon® X Elite 4.276 ms 12 - 12 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Gen 3 Mobile 2.897 ms 0 - 94 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Gen 1 Mobile 6.424 ms 1 - 103 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-8275 4.506 ms 1 - 5 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.095 ms 0 - 15 MB NPU
Mobile-VIT ONNX float Qualcomm® QCS8450 6.424 ms 1 - 103 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-9075 4.71 ms 1 - 4 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-X7181 4.276 ms 12 - 12 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ Q-8750 2.294 ms 0 - 65 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.708 ms 0 - 94 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.031 ms 0 - 89 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® X2 Elite 1.76 ms 1 - 1 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® X Elite 4.423 ms 6 - 6 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.787 ms 0 - 123 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 4.803 ms 0 - 121 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 9.876 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 3.827 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.229 ms 0 - 9 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® QCS8450 4.803 ms 0 - 121 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 4.471 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.423 ms 6 - 6 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 20.424 ms 0 - 206 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 4.657 ms 0 - 201 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.031 ms 0 - 89 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 4.657 ms 0 - 201 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.869 ms 1 - 60 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.236 ms 0 - 58 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® X2 Elite 2.316 ms 1 - 1 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® X Elite 4.393 ms 1 - 1 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.8 ms 0 - 86 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.249 ms 0 - 94 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.297 ms 1 - 4 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.984 ms 1 - 3 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8775P 4.745 ms 1 - 62 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8650P 4.745 ms 1 - 62 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8255P 4.745 ms 1 - 62 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® QCS8450 6.249 ms 0 - 94 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.564 ms 1 - 4 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 4.393 ms 1 - 1 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ Q-8750 2.236 ms 0 - 58 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8295P 7.082 ms 0 - 63 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.748 ms 0 - 81 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.11 ms 0 - 74 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® X2 Elite 2.112 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® X Elite 4.859 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.919 ms 0 - 97 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 3.95 ms 0 - 4 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.447 ms 0 - 2 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8775P 4.919 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8650P 4.919 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8255P 4.919 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 4.698 ms 0 - 3 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.859 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 17.402 ms 0 - 190 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 4.872 ms 0 - 187 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.11 ms 0 - 74 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 4.872 ms 0 - 187 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.87 ms 0 - 69 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.238 ms 0 - 78 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Gen 3 Mobile 2.818 ms 0 - 103 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Gen 1 Mobile 6.282 ms 0 - 108 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.329 ms 0 - 16 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.973 ms 0 - 2 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA8775P 4.743 ms 0 - 76 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA8650P 4.743 ms 0 - 76 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA8255P 4.743 ms 0 - 76 MB NPU
Mobile-VIT TFLITE float Qualcomm® QCS8450 6.282 ms 0 - 108 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.544 ms 0 - 16 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ Q-8750 2.238 ms 0 - 78 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA7255P 10.794 ms 0 - 73 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA8295P 7.124 ms 0 - 67 MB NPU

License

  • The license for the original implementation of Mobile-VIT 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/Mobile-VIT