> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-models-support/importing-models/common-models.md).

# Common Models

Guides for deploying common image classification and object detection models.

The Nx toolkit currently supports image classification and object detection models. Ready-made guides export the most common ones to an ONNX file that the AI Manager accepts.

## Object detection

| Model                                       | Guide                                                                                                  |
| ------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
| YOLO26 (Ultralytics)                        | [`yolo26-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolo26-to-onnx)           |
| YOLOv12                                     | [`yolov12-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov12-to-onnx)         |
| YOLOv10                                     | [`yolov10-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov10-to-onnx)         |
| YOLOv9                                      | [`yolov9-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov9-to-onnx)           |
| YOLOv9 (MultimediaTechLab/YOLO)             | [`yolov9-mit-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov9-mit-to-onnx)   |
| YOLOv7                                      | [`yolov7-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov7-to-onnx)           |
| YOLOv7 (MultimediaTechLab/YOLO)             | [`yolov7-mit-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov7-mit-to-onnx)   |
| YOLOv5                                      | [`yolov5-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov5-to-onnx)           |
| YOLOv4                                      | [`yolov4-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolov4-to-onnx)           |
| YOLOX                                       | [`yolox-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/yolox-to-onnx)             |
| YOLOv8, YOLO11 and other Ultralytics models | [`ultralytics-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/ultralytics-to-onnx) |
| RF-DETR                                     | [`rf-detr-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/rf-detr-to-onnx)         |

## Image classification

| Model                                                                                                                    | Guide                                                                                                |
| ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------- |
| MobileNet, ResNet, EfficientNet, ViT, LeViT and other [timm](https://github.com/huggingface/pytorch-image-models) models | [`timm-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/timm-to-onnx)             |
| OpenAI CLIP                                                                                                              | [`openaiCLIP-to-onnx`](https://github.com/scailable/nxai-model-to-onnx/tree/main/openaiCLIP-to-onnx) |

## What the guides do

1. Incorporate the necessary post-processing steps directly into the ONNX graph: masking and a configurable Non-Maximum Suppression (NMS) for object detection models (NMS-free models such as YOLO26 and RF-DETR use a confidence filter instead), and Softmax for image classification models.
2. Modify the model's input and output shapes and names as per the requirements of the AI Manager (see [ONNX requirements](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-models-support/custom-models/onnx-requirements.md)).
3. Make sure the exported ONNX has an Operator Set Version up to 16.

These guides give AI developers off-the-shelf scripts to deploy these models within minutes.

{% hint style="info" %}
All guides are in the [nxai-model-to-onnx](https://github.com/scailable/nxai-model-to-onnx) GitHub repository. Check the licence of the model you export before using it commercially: several of these model families are not permissively licensed.
{% endhint %}
