---
library_name: pytorch
license: other
tags:
- backbone
- bu_auto
- android
pipeline_tag: image-classification

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/web-assets/model_demo.png)

# ResNeXt50: Optimized for Qualcomm Devices

ResNeXt50 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 ResNeXt50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.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/blob/main/src/qai_hub_models/models/resnext50) 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.com) 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 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext50/releases/v0.54.0/resnext50-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[ResNeXt50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnext50)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/resnext50) 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 [ResNeXt50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/resnext50) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 25.0M
- Model size (float): 95.4 MB
- Model size (w8a8): 24.8 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| ResNeXt50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.144 ms | 1 - 86 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® 8 Elite Mobile | 1.379 ms | 0 - 84 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® X2 Elite | 1.095 ms | 50 - 50 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® X Elite | 2.424 ms | 50 - 50 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® X Elite | 2.424 ms | 50 - 50 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.679 ms | 0 - 148 MB | NPU
| ResNeXt50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.24 ms | 0 - 40 MB | NPU
| ResNeXt50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.379 ms | 0 - 84 MB | NPU
| ResNeXt50 | ONNX | float | Qualcomm® QCS9075 | 3.451 ms | 0 - 4 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.609 ms | 0 - 79 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.697 ms | 0 - 79 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.514 ms | 25 - 25 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® X Elite | 1.27 ms | 25 - 25 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® X Elite | 1.27 ms | 25 - 25 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.825 ms | 0 - 104 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Qualcomm® QCS6490 | 47.935 ms | 5 - 23 MB | CPU
| ResNeXt50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.121 ms | 0 - 33 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 20.704 ms | 3 - 13 MB | CPU
| ResNeXt50 | ONNX | w8a8 | Qualcomm® QCM6690 | 26.428 ms | 2 - 12 MB | CPU
| ResNeXt50 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.234 ms | 0 - 3 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.697 ms | 0 - 79 MB | NPU
| ResNeXt50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 20.704 ms | 3 - 13 MB | CPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.176 ms | 0 - 74 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.473 ms | 0 - 73 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® X2 Elite | 1.433 ms | 1 - 1 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® X Elite | 2.686 ms | 1 - 1 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® X Elite | 2.686 ms | 1 - 1 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.786 ms | 0 - 133 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.521 ms | 1 - 2 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® SA8775P | 3.808 ms | 1 - 72 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® SA8775P | 3.808 ms | 1 - 72 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® SA8775P | 3.808 ms | 1 - 72 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® SA7255P | 12.022 ms | 1 - 71 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 4.015 ms | 0 - 112 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® SA8295P | 4.115 ms | 0 - 52 MB | NPU
| ResNeXt50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.473 ms | 0 - 73 MB | NPU
| ResNeXt50 | QNN_DLC | float | Qualcomm® QCS9075 | 3.639 ms | 1 - 3 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.534 ms | 0 - 75 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.63 ms | 0 - 72 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.623 ms | 0 - 0 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.245 ms | 0 - 0 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.245 ms | 0 - 0 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.794 ms | 0 - 99 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.121 ms | 0 - 2 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.117 ms | 0 - 106 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.456 ms | 0 - 71 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.456 ms | 0 - 71 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.456 ms | 0 - 71 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.374 ms | 0 - 76 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 7.604 ms | 0 - 194 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.21 ms | 0 - 2 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.63 ms | 0 - 72 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.459 ms | 0 - 101 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.45 ms | 0 - 70 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.761 ms | 0 - 68 MB | NPU
| ResNeXt50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.374 ms | 0 - 76 MB | NPU
| ResNeXt50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.183 ms | 0 - 116 MB | NPU
| ResNeXt50 | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.432 ms | 0 - 116 MB | NPU
| ResNeXt50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.769 ms | 0 - 175 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.48 ms | 0 - 2 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® SA8775P | 3.83 ms | 0 - 112 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® SA8775P | 3.83 ms | 0 - 112 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® SA8775P | 3.83 ms | 0 - 112 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® SA7255P | 12.055 ms | 0 - 112 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.997 ms | 0 - 152 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® SA8295P | 4.176 ms | 0 - 87 MB | NPU
| ResNeXt50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.432 ms | 0 - 116 MB | NPU
| ResNeXt50 | TFLITE | float | Qualcomm® QCS9075 | 3.711 ms | 0 - 52 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.489 ms | 0 - 73 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.563 ms | 0 - 73 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.667 ms | 0 - 99 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.826 ms | 0 - 27 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.893 ms | 0 - 132 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.272 ms | 0 - 71 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.272 ms | 0 - 71 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.272 ms | 0 - 71 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.219 ms | 0 - 70 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 7.354 ms | 0 - 198 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.995 ms | 0 - 27 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.563 ms | 0 - 73 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.286 ms | 0 - 101 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.199 ms | 0 - 70 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.557 ms | 0 - 65 MB | NPU
| ResNeXt50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.219 ms | 0 - 70 MB | NPU

## License
* The license for the original implementation of ResNeXt50 can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/abs/1611.05431)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).