> 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-Instruct

> Reference SmolVLM-Instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.

[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.

Use this page as a checkpoint and architecture reference. 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).

## Model Reference

### Model Architecture

| Property                  | Value                                                 |
| ------------------------- | ----------------------------------------------------- |
| Task                      | Image-Text-to-Text                                    |
| Architecture              | `SmolVLMForConditionalGeneration`                     |
| Parameters                | 2.25B                                                 |
| Hugging Face Organization | [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) |

### Available Models

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

## Related Resources

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