Hugging Face's logo

qualcomm
/
MobileNet-v3-Large

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community

MobileNet-v3-Large: Optimized for Qualcomm Devices

MobileNet-v3-Large 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 MobileNet-v3-Large 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 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MobileNet-v3-Large 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 MobileNet-v3-Large 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): 20.9 MB
  • Model size (w8a16): 6.35 MB
  • Number of parameters: 5.47M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v3-Large ONNX float Snapdragon® X2 Elite 0.322 ms 2 - 2 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.73 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.491 ms 0 - 53 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 1 Mobile 1.23 ms 1 - 59 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-8275 0.941 ms 0 - 4 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.705 ms 0 - 15 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8450 1.23 ms 1 - 59 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-9075 0.962 ms 1 - 3 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.73 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ Q-8750 0.401 ms 0 - 31 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Mobile 0.401 ms 0 - 31 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.36 ms 0 - 32 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X2 Elite 0.308 ms 1 - 1 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.714 ms 7 - 7 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.474 ms 0 - 63 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.973 ms 0 - 69 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 2.885 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.753 ms 0 - 4 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.699 ms 0 - 10 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8450 0.973 ms 0 - 69 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.833 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.714 ms 7 - 7 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 3.48 ms 0 - 158 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 0.769 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.354 ms 0 - 46 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Mobile 0.354 ms 0 - 46 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.284 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.769 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® X2 Elite 0.278 ms 1 - 1 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® X Elite 0.532 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.376 ms 0 - 59 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.727 ms 0 - 65 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.608 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.618 ms 0 - 4 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.538 ms 0 - 94 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® QCS8450 0.727 ms 0 - 65 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.65 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.532 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 1.981 ms 0 - 42 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.538 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.337 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Elite Mobile 0.337 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.289 ms 0 - 40 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.538 ms 0 - 41 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.523 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.186 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.678 ms 0 - 56 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.902 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.141 ms 1 - 4 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 2.921 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.023 ms 1 - 2 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.361 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8650P 1.361 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8255P 1.361 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 1.902 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.221 ms 1 - 3 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.186 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.516 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.921 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.837 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Mobile 0.516 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.427 ms 1 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X2 Elite 0.493 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.087 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.66 ms 0 - 52 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.226 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 3.366 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 0.938 ms 0 - 3 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 2.089 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.944 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.156 ms 0 - 40 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8650P 1.156 ms 0 - 40 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8255P 1.156 ms 0 - 40 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 1.226 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.035 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.087 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 4.35 ms 0 - 151 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.017 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.465 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.089 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.583 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.465 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.37 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.017 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® X2 Elite 0.314 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® X Elite 0.627 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.36 ms 0 - 50 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.726 ms 0 - 55 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.735 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.532 ms 0 - 3 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.186 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.5 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8775P 0.693 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8650P 0.693 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8255P 0.693 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® QCS8450 0.726 ms 0 - 55 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.582 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.627 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.264 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.572 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.262 ms 0 - 34 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA7255P 1.186 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.262 ms 0 - 34 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.219 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.572 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 3 Mobile 0.7 ms 0 - 56 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 1 Mobile 1.911 ms 0 - 63 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.202 ms 0 - 16 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.071 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.036 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.429 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8650P 1.429 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8255P 1.429 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8450 1.911 ms 0 - 63 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.267 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ Q-8750 0.529 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.071 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.86 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Mobile 0.529 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.435 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.237 ms 0 - 49 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.538 ms 0 - 55 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.287 ms 0 - 10 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.386 ms 0 - 9 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.904 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.331 ms 0 - 25 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8775P 0.527 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8650P 0.527 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8255P 0.527 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® QCS8450 0.538 ms 0 - 55 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.418 ms 0 - 8 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 1.682 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.395 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.197 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA7255P 0.904 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8295P 0.804 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.197 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.165 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.395 ms 0 - 32 MB NPU

License

  • The license for the original implementation of MobileNet-v3-Large 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/MobileNet-v3-Large