Hugging Face's logo

qualcomm
/
VIT

Image Classification
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community

VIT: Optimized for Mobile Deployment

Imagenet classifier and general purpose backbone

VIT 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 model is an implementation of VIT found here.

This repository provides scripts to run VIT on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Model_use_case.image_classification
  • Model Stats:
    • Model checkpoint: Imagenet
    • Input resolution: 224x224
    • Number of parameters: 86.6M
    • Model size (float): 330 MB
    • Model size (w8a16): 86.2 MB
    • Model size (w8a8): 83.2 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
VIT float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 36.645 ms 0 - 300 MB NPU VIT.tflite
VIT float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 40.171 ms 1 - 302 MB NPU VIT.dlc
VIT float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 12.467 ms 0 - 310 MB NPU VIT.tflite
VIT float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 19.979 ms 0 - 312 MB NPU VIT.dlc
VIT float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 8.494 ms 0 - 19 MB NPU VIT.tflite
VIT float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 10.929 ms 0 - 27 MB NPU VIT.dlc
VIT float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 13.374 ms 0 - 26 MB NPU VIT.onnx.zip
VIT float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 11.344 ms 0 - 301 MB NPU VIT.tflite
VIT float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 13.943 ms 0 - 302 MB NPU VIT.dlc
VIT float SA7255P ADP Qualcomm® SA7255P TFLITE 36.645 ms 0 - 300 MB NPU VIT.tflite
VIT float SA7255P ADP Qualcomm® SA7255P QNN_DLC 40.171 ms 1 - 302 MB NPU VIT.dlc
VIT float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 8.479 ms 0 - 28 MB NPU VIT.tflite
VIT float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 11.181 ms 0 - 26 MB NPU VIT.dlc
VIT float SA8295P ADP Qualcomm® SA8295P TFLITE 14.229 ms 0 - 302 MB NPU VIT.tflite
VIT float SA8295P ADP Qualcomm® SA8295P QNN_DLC 17.096 ms 1 - 307 MB NPU VIT.dlc
VIT float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 8.116 ms 0 - 60 MB NPU VIT.tflite
VIT float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 11.219 ms 0 - 22 MB NPU VIT.dlc
VIT float SA8775P ADP Qualcomm® SA8775P TFLITE 11.344 ms 0 - 301 MB NPU VIT.tflite
VIT float SA8775P ADP Qualcomm® SA8775P QNN_DLC 13.943 ms 0 - 302 MB NPU VIT.dlc
VIT float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 5.988 ms 0 - 307 MB NPU VIT.tflite
VIT float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 7.741 ms 1 - 310 MB NPU VIT.dlc
VIT float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 9.113 ms 0 - 326 MB NPU VIT.onnx.zip
VIT float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 4.142 ms 0 - 305 MB NPU VIT.tflite
VIT float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 5.549 ms 0 - 308 MB NPU VIT.dlc
VIT float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 6.403 ms 1 - 325 MB NPU VIT.onnx.zip
VIT float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 3.642 ms 0 - 303 MB NPU VIT.tflite
VIT float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 4.232 ms 1 - 305 MB NPU VIT.dlc
VIT float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 4.862 ms 1 - 318 MB NPU VIT.onnx.zip
VIT float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 11.88 ms 1100 - 1100 MB NPU VIT.dlc
VIT float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 13.885 ms 171 - 171 MB NPU VIT.onnx.zip
VIT w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 70.308 ms 0 - 194 MB NPU VIT.dlc
VIT w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 27.051 ms 0 - 45 MB NPU VIT.dlc
VIT w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 304.034 ms 30 - 122 MB NPU VIT.onnx.zip
VIT w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 24.559 ms 0 - 189 MB NPU VIT.dlc
VIT w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 525.765 ms 85 - 102 MB CPU VIT.onnx.zip
VIT w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 567.411 ms 87 - 102 MB CPU VIT.onnx.zip
VIT w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 70.308 ms 0 - 194 MB NPU VIT.dlc
VIT w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 26.91 ms 0 - 46 MB NPU VIT.dlc
VIT w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 26.873 ms 0 - 44 MB NPU VIT.dlc
VIT w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 24.559 ms 0 - 189 MB NPU VIT.dlc
VIT w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 19.879 ms 0 - 204 MB NPU VIT.dlc
VIT w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 260.409 ms 53 - 91 MB NPU VIT.onnx.zip
VIT w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 15.874 ms 0 - 191 MB NPU VIT.dlc
VIT w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 297.138 ms 55 - 95 MB NPU VIT.onnx.zip
VIT w8a16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 43.457 ms 0 - 255 MB NPU VIT.dlc
VIT w8a16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 595.119 ms 66 - 82 MB CPU VIT.onnx.zip
VIT w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 12.888 ms 0 - 195 MB NPU VIT.dlc
VIT w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 198.485 ms 53 - 97 MB NPU VIT.onnx.zip
VIT w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 27.131 ms 277 - 277 MB NPU VIT.dlc
VIT w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 159.494 ms 63 - 63 MB NPU VIT.onnx.zip
VIT w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 15.551 ms 0 - 48 MB NPU VIT.tflite
VIT w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 29.907 ms 0 - 150 MB NPU VIT.dlc
VIT w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 8.11 ms 0 - 60 MB NPU VIT.tflite
VIT w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 13.198 ms 0 - 267 MB NPU VIT.dlc
VIT w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 7.428 ms 0 - 20 MB NPU VIT.tflite
VIT w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 9.673 ms 0 - 23 MB NPU VIT.dlc
VIT w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 307.251 ms 31 - 121 MB NPU VIT.onnx.zip
VIT w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 7.844 ms 0 - 47 MB NPU VIT.tflite
VIT w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 9.511 ms 0 - 150 MB NPU VIT.dlc
VIT w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 61.128 ms 2 - 47 MB NPU VIT.tflite
VIT w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 77.949 ms 0 - 661 MB NPU VIT.dlc
VIT w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 438.387 ms 68 - 86 MB CPU VIT.onnx.zip
VIT w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 493.483 ms 73 - 85 MB CPU VIT.onnx.zip
VIT w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 15.551 ms 0 - 48 MB NPU VIT.tflite
VIT w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 29.907 ms 0 - 150 MB NPU VIT.dlc
VIT w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 7.42 ms 0 - 19 MB NPU VIT.tflite
VIT w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 10.22 ms 0 - 24 MB NPU VIT.dlc
VIT w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 9.768 ms 0 - 49 MB NPU VIT.tflite
VIT w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 16.394 ms 0 - 165 MB NPU VIT.dlc
VIT w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 7.449 ms 0 - 21 MB NPU VIT.tflite
VIT w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 10.202 ms 0 - 22 MB NPU VIT.dlc
VIT w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 7.844 ms 0 - 47 MB NPU VIT.tflite
VIT w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 9.511 ms 0 - 150 MB NPU VIT.dlc
VIT w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 5.252 ms 0 - 57 MB NPU VIT.tflite
VIT w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 6.907 ms 0 - 156 MB NPU VIT.dlc
VIT w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 249.531 ms 52 - 91 MB NPU VIT.onnx.zip
VIT w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 4.078 ms 0 - 54 MB NPU VIT.tflite
VIT w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 5.792 ms 0 - 153 MB NPU VIT.dlc
VIT w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 205.336 ms 57 - 95 MB NPU VIT.onnx.zip
VIT w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile TFLITE 22.784 ms 1 - 33 MB NPU VIT.tflite
VIT w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 18.157 ms 0 - 170 MB NPU VIT.dlc
VIT w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 483.82 ms 66 - 84 MB CPU VIT.onnx.zip
VIT w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 3.46 ms 0 - 55 MB NPU VIT.tflite
VIT w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 3.782 ms 0 - 258 MB NPU VIT.dlc
VIT w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 194.367 ms 52 - 95 MB NPU VIT.onnx.zip
VIT w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 10.809 ms 439 - 439 MB NPU VIT.dlc
VIT w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 178.816 ms 60 - 60 MB NPU VIT.onnx.zip
VIT w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 371.606 ms 43 - 152 MB NPU VIT.onnx.zip
VIT w8a8_mixed_int16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 533.886 ms 72 - 91 MB CPU VIT.onnx.zip
VIT w8a8_mixed_int16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 515.386 ms 86 - 106 MB CPU VIT.onnx.zip
VIT w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 306.677 ms 78 - 119 MB NPU VIT.onnx.zip
VIT w8a8_mixed_int16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 303.831 ms 78 - 118 MB NPU VIT.onnx.zip
VIT w8a8_mixed_int16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 508.832 ms 91 - 110 MB CPU VIT.onnx.zip
VIT w8a8_mixed_int16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 242.334 ms 79 - 122 MB NPU VIT.onnx.zip
VIT w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 320.981 ms 133 - 133 MB NPU VIT.onnx.zip

Installation

Install the package via pip:

pip install qai-hub-models

Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub Workbench with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.vit.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.vit.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.vit.export

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.vit import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S25")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub Workbench. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.vit.demo --eval-mode on-device

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.vit.demo -- --eval-mode on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on VIT's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of VIT can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
372
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support