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 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.30.0 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 1.929 ms 0 - 66 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.296 ms 0 - 63 MB NPU
Mobile-VIT ONNX float Snapdragon® X2 Elite 2.128 ms 2 - 2 MB NPU
Mobile-VIT ONNX float Snapdragon® X Elite 4.287 ms 12 - 12 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Gen 3 Mobile 2.891 ms 0 - 96 MB NPU
Mobile-VIT ONNX float Snapdragon® 8 Gen 1 Mobile 6.461 ms 1 - 103 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-8275 4.496 ms 1 - 5 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.09 ms 0 - 71 MB NPU
Mobile-VIT ONNX float Qualcomm® QCS8450 6.461 ms 1 - 103 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-9075 4.72 ms 1 - 4 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ IQ-X7181 4.287 ms 12 - 12 MB NPU
Mobile-VIT ONNX float Qualcomm® Dragonwing™ Q-8750 2.296 ms 0 - 63 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.707 ms 0 - 94 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.025 ms 0 - 88 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® X2 Elite 1.754 ms 1 - 1 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® X Elite 4.376 ms 6 - 6 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.783 ms 0 - 120 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 4.805 ms 0 - 123 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 9.713 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 3.833 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.216 ms 0 - 105 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® QCS8450 4.805 ms 0 - 123 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 4.47 ms 0 - 4 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.376 ms 6 - 6 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 19.98 ms 0 - 205 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 4.633 ms 0 - 201 MB NPU
Mobile-VIT ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.025 ms 0 - 88 MB NPU
Mobile-VIT ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 4.633 ms 0 - 201 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.851 ms 0 - 61 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.233 ms 1 - 65 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® X2 Elite 2.304 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 2.802 ms 0 - 86 MB NPU
Mobile-VIT QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.223 ms 0 - 93 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) 3.978 ms 1 - 3 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8650P 4.73 ms 1 - 62 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8255P 4.73 ms 1 - 62 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® QCS8450 6.223 ms 0 - 93 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.533 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 2.233 ms 1 - 65 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA7255P 10.787 ms 1 - 59 MB NPU
Mobile-VIT QNN_DLC float Qualcomm® SA8295P 7.1 ms 0 - 63 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.749 ms 0 - 81 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.105 ms 0 - 73 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® X2 Elite 2.17 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® X Elite 4.87 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.907 ms 0 - 102 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 3.947 ms 0 - 4 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.439 ms 0 - 2 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8775P 4.89 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8650P 4.89 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA8255P 4.89 ms 0 - 77 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 4.704 ms 2 - 5 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.87 ms 0 - 0 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 17.655 ms 0 - 191 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 4.961 ms 0 - 187 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.105 ms 0 - 73 MB NPU
Mobile-VIT QNN_DLC w8a16 Qualcomm® SA7255P 7.943 ms 0 - 75 MB NPU
Mobile-VIT QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 4.961 ms 0 - 187 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.845 ms 0 - 82 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.239 ms 0 - 79 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Gen 3 Mobile 2.815 ms 0 - 104 MB NPU
Mobile-VIT TFLITE float Snapdragon® 8 Gen 1 Mobile 6.236 ms 0 - 99 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.308 ms 0 - 16 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.978 ms 0 - 5 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 6.236 ms 0 - 99 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.547 ms 0 - 16 MB NPU
Mobile-VIT TFLITE float Qualcomm® Dragonwing™ Q-8750 2.239 ms 0 - 79 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA7255P 10.824 ms 0 - 72 MB NPU
Mobile-VIT TFLITE float Qualcomm® SA8295P 7.125 ms 0 - 66 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Mobile-VIT