Hugging Face's logo

qualcomm
/
MobileNet-v3-Small

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

MobileNet-v3-Small: Optimized for Qualcomm Devices

MobileNetV3Small 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-Small 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
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MobileNet-v3-Small 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-Small on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 2.54M
  • Model size (float): 9.71 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v3-Small ONNX float Snapdragon® X2 Elite 0.244 ms 2 - 2 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® X Elite 0.551 ms 6 - 6 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Gen 3 Mobile 0.351 ms 0 - 45 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Gen 1 Mobile 0.866 ms 1 - 51 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.549 ms 0 - 8 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® QCS8450 0.866 ms 1 - 51 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ IQ-9075 0.707 ms 1 - 3 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.551 ms 6 - 6 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ Q-8750 0.287 ms 0 - 29 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Elite Mobile 0.287 ms 0 - 29 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.252 ms 0 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® X2 Elite 0.44 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® X Elite 0.957 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.55 ms 0 - 43 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.586 ms 0 - 50 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ QCS8275 2.078 ms 1 - 28 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.831 ms 1 - 2 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8775P 1.095 ms 1 - 32 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8650P 1.095 ms 1 - 32 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8255P 1.095 ms 1 - 32 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® QCS8450 1.586 ms 0 - 50 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 0.977 ms 3 - 5 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 0.957 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.412 ms 0 - 33 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA7255P 2.078 ms 1 - 28 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8295P 1.454 ms 1 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Elite Mobile 0.412 ms 0 - 33 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.323 ms 1 - 31 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® X2 Elite 0.428 ms 0 - 0 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® X Elite 0.944 ms 0 - 0 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.554 ms 0 - 39 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 0.99 ms 0 - 47 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 2.744 ms 0 - 2 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8275 1.772 ms 0 - 28 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.795 ms 0 - 2 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8775P 1.015 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8650P 1.015 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8255P 1.015 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® QCS8450 0.99 ms 0 - 47 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 0.904 ms 2 - 4 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.944 ms 0 - 0 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 2.83 ms 0 - 141 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 0.811 ms 0 - 27 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.377 ms 0 - 31 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA7255P 1.772 ms 0 - 28 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8295P 1.324 ms 0 - 27 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.377 ms 0 - 31 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.315 ms 0 - 27 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.811 ms 0 - 27 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Gen 3 Mobile 0.56 ms 0 - 45 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Gen 1 Mobile 1.594 ms 0 - 50 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ QCS8275 2.154 ms 0 - 30 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.835 ms 0 - 2 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8775P 1.152 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8650P 1.152 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8255P 1.152 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® QCS8450 1.594 ms 0 - 50 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.013 ms 0 - 8 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ Q-8750 0.423 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA7255P 2.154 ms 0 - 30 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8295P 1.494 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Elite Mobile 0.423 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.32 ms 0 - 31 MB NPU

License

  • The license for the original implementation of MobileNet-v3-Small 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

Model tree for qualcomm/MobileNet-v3-Small

Quantizations
1 model

Paper for qualcomm/MobileNet-v3-Small