> 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.

# InternVL

[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.

|                  |                                               |
| ---------------- | --------------------------------------------- |
| **Task**         | Image-Text-to-Text                            |
| **Architecture** | `InternVLForConditionalGeneration`            |
| **Parameters**   | 4B – 8B                                       |
| **HF Org**       | [OpenGVLab](https://huggingface.co/OpenGVLab) |

## Available Models

* **InternVL3.5-4B**
* **InternVL3.5-8B**

## Architecture

* `InternVLForConditionalGeneration`

## Example HF Models

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

## Example Recipes

| Recipe                                                                                                                            | Dataset    | Description                    |
| --------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------------------ |
| [internvl\_3\_5\_4b.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/internvl/internvl_3_5_4b.yaml) | MedPix-VQA | SFT — InternVL3.5 4B on MedPix |

## Try with NeMo AutoModel

**1. Install** ([full instructions](/get-started/installation)):

```bash
pip install nemo-automodel
```

**2. Clone the repo** to get the example recipes:

```bash
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
```

**3. Run the recipe** from inside the repo:

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

**1. Pull the container** and mount a checkpoint directory:

```bash
docker run --gpus all -it --rm \
  --shm-size=8g \
  -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
  nvcr.io/nvidia/nemo-automodel:26.06.00
```

**2.** Navigate to the AutoModel directory (where the recipes are):

```bash
cd /opt/Automodel
```

**3. Run the recipe**:

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

See the [Installation Guide](/get-started/installation) and [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n).

## Fine-Tuning

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

## Hugging Face Model Cards

* [OpenGVLab/InternVL3\_5-4B](https://huggingface.co/OpenGVLab/InternVL3_5-4B)