> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/changelog/explore-by-month/november-2025/train-dinov3-models-on-roboflow.md).

# 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.