> 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.

# Gemma 3 VL / Gemma 3n

[Gemma 3 VL](https://ai.google.dev/gemma/docs/core) is Google's multimodal extension of Gemma 3, supporting image-text inputs for tasks like image captioning and visual question answering. Gemma 3n is a next-generation efficiency-focused variant.

|                  |                                         |
| ---------------- | --------------------------------------- |
| **Task**         | Image-Text-to-Text                      |
| **Architecture** | `Gemma3ForConditionalGeneration`        |
| **Parameters**   | 4B – 27B                                |
| **HF Org**       | [google](https://huggingface.co/google) |

## Available Models

* **Gemma 3 27B IT** (VL)
* **Gemma 3 4B IT** (VL)
* **Gemma 3n 4B** (VL)

## Architecture

* `Gemma3ForConditionalGeneration`

## Example HF Models

| Model          | HF ID                                                                   |
| -------------- | ----------------------------------------------------------------------- |
| Gemma 3 4B IT  | [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it)   |
| Gemma 3 27B IT | [`google/gemma-3-27b-it`](https://huggingface.co/google/gemma-3-27b-it) |

## Example Recipes

| Recipe                                                                                                                                                                   | Dataset    | Description                           |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | ------------------------------------- |
| [gemma3\_vl\_4b\_cord\_v2.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml)                               | cord-v2    | SFT — Gemma 3 4B VL on CORD-v2        |
| [gemma3\_vl\_4b\_cord\_v2\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2_peft.yaml)                    | cord-v2    | LoRA — Gemma 3 4B VL on CORD-v2       |
| [gemma3\_vl\_4b\_cord\_v2\_megatron\_fsdp.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2_megatron_fsdp.yaml) | cord-v2    | SFT — Gemma 3 4B VL with MegatronFSDP |
| [gemma3\_vl\_4b\_medpix.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3/gemma3_vl_4b_medpix.yaml)                                  | MedPix-VQA | SFT — Gemma 3 4B VL on MedPix         |
| [gemma3n\_vl\_4b\_medpix.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3n/gemma3n_vl_4b_medpix.yaml)                               | MedPix-VQA | SFT — Gemma 3n 4B VL on MedPix        |
| [gemma3n\_vl\_4b\_medpix\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/gemma3n/gemma3n_vl_4b_medpix_peft.yaml)                    | MedPix-VQA | LoRA — Gemma 3n 4B VL 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/gemma3/gemma3_vl_4b_cord_v2.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/gemma3/gemma3_vl_4b_cord_v2.yaml
```

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

## Fine-Tuning

See the [Gemma 3 & Gemma 3n Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n) for detailed instructions on dataset preparation, configuration, and multi-GPU training.

## Hugging Face Model Cards

* [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
* [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it)