Hugging Face's logo

qualcomm
/
EfficientNet-Lite4

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community

EfficientNet-Lite4: Optimized for Qualcomm Devices

EfficientNet-Lite4 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 EfficientNet-Lite4 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 w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float 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 EfficientNet-Lite4 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 EfficientNet-Lite4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: Imagenet
  • Input resolution: 300x300
  • Number of parameters: 13.01M
  • Model size (float): 51.9 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
EfficientNet-Lite4 ONNX float Snapdragon® X2 Elite 1.444 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® X Elite 2.752 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 3 Mobile 1.91 ms 0 - 100 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 1 Mobile 5.512 ms 0 - 98 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.626 ms 0 - 182 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® QCS8450 5.512 ms 0 - 98 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-9075 4.121 ms 1 - 4 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.752 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ Q-8750 1.5 ms 0 - 55 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite Mobile 1.5 ms 0 - 55 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.145 ms 1 - 58 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X2 Elite 0.647 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X Elite 1.271 ms 16 - 16 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.878 ms 0 - 110 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 2.07 ms 0 - 117 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.982 ms 0 - 3 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.234 ms 0 - 18 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® QCS8450 2.07 ms 0 - 117 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.418 ms 0 - 3 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.271 ms 16 - 16 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.713 ms 0 - 73 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.713 ms 0 - 73 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.601 ms 0 - 72 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X2 Elite 1.883 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X Elite 3.498 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.206 ms 1 - 103 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.878 ms 0 - 99 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ QCS8275 15.287 ms 1 - 53 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.125 ms 1 - 124 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8775P 4.788 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8650P 4.788 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8255P 4.788 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® QCS8450 6.878 ms 0 - 99 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.54 ms 1 - 4 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.498 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.687 ms 1 - 54 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA7255P 15.287 ms 1 - 53 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8295P 6.434 ms 1 - 50 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite Mobile 1.687 ms 1 - 54 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.27 ms 1 - 57 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® X2 Elite 0.748 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® X Elite 1.435 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.902 ms 0 - 98 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.341 ms 0 - 106 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 7.137 ms 2 - 4 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8275 3.354 ms 0 - 63 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.243 ms 0 - 2 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8775P 1.613 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8650P 1.613 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8255P 1.613 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® QCS8450 2.341 ms 0 - 106 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.419 ms 0 - 2 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.435 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 11.258 ms 0 - 184 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.624 ms 0 - 65 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.655 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA7255P 3.354 ms 0 - 63 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8295P 2.537 ms 0 - 61 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.655 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.51 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.624 ms 0 - 65 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 3 Mobile 2.191 ms 0 - 113 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 1 Mobile 6.687 ms 0 - 112 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ QCS8275 15.322 ms 0 - 65 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.137 ms 0 - 3 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8775P 4.793 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8650P 4.793 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8255P 4.793 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® QCS8450 6.687 ms 0 - 112 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.534 ms 0 - 32 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ Q-8750 1.689 ms 0 - 69 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA7255P 15.322 ms 0 - 65 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8295P 6.437 ms 0 - 48 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite Mobile 1.689 ms 0 - 69 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.258 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.65 ms 0 - 100 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.771 ms 0 - 103 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 5.993 ms 0 - 31 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8275 2.778 ms 0 - 59 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.92 ms 0 - 2 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8775P 1.29 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8650P 1.29 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8255P 1.29 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® QCS8450 1.771 ms 0 - 103 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.072 ms 0 - 17 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 10.034 ms 0 - 179 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.24 ms 0 - 174 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.517 ms 0 - 64 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA7255P 2.778 ms 0 - 59 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8295P 2.139 ms 0 - 56 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.517 ms 0 - 64 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.418 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.24 ms 0 - 174 MB NPU

License

  • The license for the original implementation of EfficientNet-Lite4 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/EfficientNet-Lite4