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 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.138 ms 0 - 60 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.503 ms 0 - 61 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® X2 Elite 1.427 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® X Elite 2.744 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 3 Mobile 1.918 ms 0 - 108 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 1 Mobile 5.326 ms 0 - 102 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-8275 4.613 ms 1 - 5 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.637 ms 1 - 3 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® QCS8450 5.326 ms 0 - 102 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-9075 4.152 ms 1 - 4 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.744 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ Q-8750 1.503 ms 0 - 61 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.588 ms 0 - 78 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.703 ms 0 - 79 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X2 Elite 0.607 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X Elite 1.248 ms 15 - 15 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.874 ms 0 - 117 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.779 ms 0 - 123 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.244 ms 0 - 4 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.316 ms 0 - 4 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.228 ms 0 - 3 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® QCS8450 1.779 ms 0 - 123 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.416 ms 0 - 3 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.248 ms 15 - 15 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.721 ms 0 - 190 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.452 ms 0 - 77 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.703 ms 0 - 79 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.452 ms 0 - 77 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.25 ms 1 - 64 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.692 ms 0 - 56 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X2 Elite 1.842 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X Elite 3.489 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.191 ms 0 - 101 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.699 ms 0 - 102 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.861 ms 1 - 5 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.144 ms 1 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® QCS8450 6.699 ms 0 - 102 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.525 ms 1 - 4 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.489 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.692 ms 0 - 56 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8295P 6.327 ms 1 - 53 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.519 ms 0 - 69 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.648 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® X2 Elite 0.714 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.895 ms 0 - 101 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.914 ms 0 - 113 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.163 ms 0 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.322 ms 0 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.281 ms 0 - 18 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8650P 1.611 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8255P 1.611 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® QCS8450 1.914 ms 0 - 113 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.406 ms 0 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 11.262 ms 0 - 183 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.591 ms 0 - 70 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.648 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8295P 2.387 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.591 ms 0 - 70 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.247 ms 0 - 73 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.682 ms 0 - 72 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 3 Mobile 2.21 ms 0 - 121 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 1 Mobile 6.495 ms 0 - 116 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.834 ms 0 - 33 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.077 ms 0 - 4 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8775P 16.255 ms 0 - 32 MB GPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8650P 16.255 ms 0 - 32 MB GPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8255P 16.255 ms 0 - 32 MB GPU
EfficientNet-Lite4 TFLITE float Qualcomm® QCS8450 6.495 ms 0 - 116 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.522 ms 0 - 33 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ Q-8750 1.682 ms 0 - 72 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA7255P 36.418 ms 0 - 28 MB GPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8295P 6.322 ms 0 - 52 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.418 ms 0 - 64 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.508 ms 0 - 62 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.656 ms 0 - 96 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.398 ms 0 - 109 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 4.683 ms 0 - 31 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.015 ms 0 - 18 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.899 ms 0 - 80 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8650P 1.278 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8255P 1.278 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® QCS8450 1.398 ms 0 - 109 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.052 ms 0 - 18 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 10.043 ms 0 - 176 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.293 ms 0 - 170 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.508 ms 0 - 62 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA7255P 37.673 ms 1 - 27 MB GPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8295P 2.003 ms 0 - 59 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.293 ms 0 - 170 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