# Train DINOv3 Models on Roboflow

<figure><img src="/files/VOTASua28LzcSy1qOOK0" alt=""><figcaption></figcaption></figure>

You can now train DINOv3 classification models on Roboflow. DINOv3 models train fast, work well across different image resolutions, and runs at a speed comparable to ViT model.

To train a DINOv3 model, create a new dataset version in a Classification project, then choose the "DINOv3" model architecture.

You can then deploy your DINOv3 model in Roboflow Workflows in the classification Workflow blocks.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.roboflow.com/changelog/explore-by-month/november-2025/train-dinov3-models-on-roboflow.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.