> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# InternVL3_5-4B

> Use InternVL3_5-4B with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[InternVL](https://github.com/OpenGVLab/InternVL) is a vision language model from Shanghai AI Laboratory (OpenGVLab), combining a large vision encoder with an InternLM language backbone for strong multimodal performance.

Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

## Fine-Tune InternVL3\_5-4B

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/vlm_finetune/internvl/internvl_3_5_4b.yaml
```

## Choose a Workflow

| Goal                                                    | Start Here                                                                                                                                                  |
| ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Supervised fine-tuning (SFT) - InternVL3.5 4B on MedPix | Use [internvl\_3\_5\_4b.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/internvl/internvl_3_5_4b.yaml). Dataset: MedPix-VQA. |

## Model Reference

### Model Architecture

| Property                  | Value                                         |
| ------------------------- | --------------------------------------------- |
| Task                      | Image-Text-to-Text                            |
| Architecture              | `InternVLForConditionalGeneration`            |
| Parameters                | 4B                                            |
| Hugging Face Organization | [OpenGVLab](https://huggingface.co/OpenGVLab) |

### Available Models

| Model             | HF ID                                                                               |
| ----------------- | ----------------------------------------------------------------------------------- |
| InternVL3.5 4B    | [`OpenGVLab/InternVL3_5-4B`](https://huggingface.co/OpenGVLab/InternVL3_5-4B)       |
| InternVL3.5 4B HF | [`OpenGVLab/InternVL3_5-4B-hf`](https://huggingface.co/OpenGVLab/InternVL3_5-4B-hf) |

## Related Resources

* [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n)