> 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.

# SmolVLM

[SmolVLM](https://huggingface.co/blog/smolvlm) is HuggingFace's compact vision language model designed for on-device and memory-constrained deployment, featuring an efficient image token compression strategy.

|                  |                                                       |
| ---------------- | ----------------------------------------------------- |
| **Task**         | Image-Text-to-Text                                    |
| **Architecture** | `SmolVLMForConditionalGeneration`                     |
| **Parameters**   | 256M – 2B                                             |
| **HF Org**       | [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) |

## Available Models

* **SmolVLM-Instruct**: 2B
* **SmolVLM-256M-Instruct**: 256M

## Architecture

* `SmolVLMForConditionalGeneration`

## Example HF Models

| Model                 | HF ID                                                                                               |
| --------------------- | --------------------------------------------------------------------------------------------------- |
| SmolVLM Instruct      | [`HuggingFaceTB/SmolVLM-Instruct`](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct)           |
| SmolVLM 256M Instruct | [`HuggingFaceTB/SmolVLM-256M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct) |

## Try with NeMo AutoModel

Install NeMo AutoModel and follow the fine-tuning guide to configure a recipe for this model.

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

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

**2. Clone the repo** to get example recipes you can adapt:

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

**3. Fine-tune** by adapting a base VLM recipe — override the model ID on the CLI:

```bash
automodel --nproc-per-node=8 examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml \
  --model.pretrained_model_name_or_path <MODEL_HF_ID>
```

Replace `<MODEL_HF_ID>` with the model ID from **Example HF Models** above.

**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:26.04.00
```

**2.** The recipes are at `/opt/Automodel/examples/` — navigate there:

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

**3. Fine-tune**:

```bash
automodel --nproc-per-node=8 examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml \
  --model.pretrained_model_name_or_path <MODEL_HF_ID>
```

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

* [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct)