---
title: EfficientNet-B4
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/EfficientNet-B4"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/EfficientNet-B4.md"
repository: Qualcomm-AI-Hub/EfficientNet-B4
last_updated: 2026-10-16
license: bsd-3-clause
pipeline_tag: image-classification
tasks:
  - image-classification
downloads: 0
stars: 0
tags:
  - backbone
  - bu_auto
  - android
---

# EfficientNet-B4

> EfficientNet-B4 - Qualcomm-AI-Hub 在 ModelScope 开源的模型。EfficientNet-B4: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/EfficientNet-B4 是 ModelScope 魔搭社区上的image-classification模型，采用 bsd-3-clause 许可。

- **Repository**: Qualcomm-AI-Hub/EfficientNet-B4
- **License**: bsd-3-clause
- **Tasks**: image-classification
- **Tags**: backbone, bu_auto, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/EfficientNet-B4

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/web-assets/model_demo.png)

# EfficientNet-B4: Optimized for Qualcomm Devices

EfficientNetB4 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-B4 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/efficientnet_b4) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/releases/v0.62.1/efficientnet_b4-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/releases/v0.62.1/efficientnet_b4-onnx-w8a16.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/releases/v0.62.1/efficientnet_b4-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/releases/v0.62.1/efficientnet_b4-qnn_dlc-w8a16.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/efficientnet_b4/releases/v0.62.1/efficientnet_b4-tflite-float.zip)

For more device-specific assets and performance metrics, visit **[EfficientNet-B4 on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/efficientnet_b4)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/efficientnet_b4) 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-B4 on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/efficientnet_b4) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Input resolution: 380x380
- Model checkpoint: Imagenet
- Model size (float): 73.6 MB
- Model size (w8a16): 24.0 MB
- Number of parameters: 19.3M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| EfficientNet-B4 | ONNX | float | Snapdragon® X2 Elite | 3.92 ms | 2 - 2 MB | NPU
| EfficientNet-B4 | ONNX | float | Snapdragon® X Elite | 7.683 ms | 45 - 45 MB | NPU
| EfficientNet-B4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.311 ms | 0 - 149 MB | NPU
| EfficientNet-B4 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 20.454 ms | 0 - 189 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.59 ms | 2 - 7 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.324 ms | 0 - 49 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® QCS8450 | 20.454 ms | 0 - 189 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.361 ms | 1 - 6 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.683 ms | 45 - 45 MB | NPU
| EfficientNet-B4 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.049 ms | 0 - 92 MB | NPU
| EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite Mobile | 4.049 ms | 0 - 92 MB | NPU
| EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.115 ms | 2 - 209 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® X2 Elite | 2.912 ms | 2 - 2 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® X Elite | 8.009 ms | 24 - 24 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.089 ms | 1 - 224 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.956 ms | 0 - 226 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 32.6 ms | 0 - 4 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.955 ms | 1 - 4 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.654 ms | 0 - 30 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® QCS8450 | 8.956 ms | 0 - 226 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.982 ms | 1 - 4 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.009 ms | 24 - 24 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 53.691 ms | 0 - 295 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.119 ms | 1 - 287 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.413 ms | 0 - 164 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.413 ms | 0 - 164 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.744 ms | 0 - 175 MB | NPU
| EfficientNet-B4 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.119 ms | 1 - 287 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® X2 Elite | 12.951 ms | 2 - 2 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® X Elite | 8.889 ms | 2 - 2 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.806 ms | 0 - 141 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 22.949 ms | 2 - 187 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 10.018 ms | 2 - 6 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.133 ms | 2 - 3 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8775P | 10.278 ms | 2 - 84 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8650P | 10.278 ms | 2 - 84 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8255P | 10.278 ms | 2 - 84 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8450 | 22.949 ms | 2 - 187 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 10.047 ms | 4 - 7 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.889 ms | 2 - 2 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.305 ms | 2 - 87 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA7255P | 29.118 ms | 2 - 81 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8295P | 18.799 ms | 2 - 124 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.305 ms | 2 - 87 MB | NPU
| EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.348 ms | 2 - 207 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.497 ms | 1 - 1 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.066 ms | 1 - 1 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.629 ms | 0 - 196 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 11.203 ms | 1 - 202 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 33.811 ms | 1 - 3 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.617 ms | 1 - 4 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.35 ms | 1 - 2 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8775P | 8.918 ms | 1 - 144 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8650P | 8.918 ms | 1 - 144 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8255P | 8.918 ms | 1 - 144 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 11.203 ms | 1 - 202 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.662 ms | 3 - 5 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 9.066 ms | 1 - 1 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 43.128 ms | 1 - 276 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.715 ms | 1 - 269 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.698 ms | 1 - 144 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 15.388 ms | 1 - 141 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 10.925 ms | 1 - 143 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.698 ms | 1 - 144 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.003 ms | 1 - 157 MB | NPU
| EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.715 ms | 1 - 269 MB | NPU
| EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.753 ms | 0 - 163 MB | NPU
| EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 21.78 ms | 0 - 204 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 9.989 ms | 0 - 50 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.066 ms | 0 - 2 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® SA8775P | 10.273 ms | 0 - 99 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® SA8650P | 10.273 ms | 0 - 99 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® SA8255P | 10.273 ms | 0 - 99 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8450 | 21.78 ms | 0 - 204 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 9.997 ms | 0 - 49 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.327 ms | 0 - 105 MB | NPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® SA7255P | 65.997 ms | 0 - 29 MB | GPU
| EfficientNet-B4 | TFLITE | float | Qualcomm® SA8295P | 18.845 ms | 0 - 140 MB | NPU
| EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.327 ms | 0 - 105 MB | NPU
| EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.318 ms | 0 - 97 MB | NPU

## License
* The license for the original implementation of EfficientNet-B4 can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).