> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/poolside/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Poolside

> Browse NeMo AutoModel coverage for Poolside large language models.

* [`Laguna-S-2.1`](/model-coverage/large-language-models/poolside/Laguna-S-2.1)
* [`Laguna-XS-2.1`](/model-coverage/large-language-models/poolside/Laguna-XS-2.1)

> Browse NeMo AutoModel coverage for Poolside large language models.

## Docs

- [Laguna-S-2.1](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/poolside/Laguna-S-2.1.md): Fine-tune Laguna-S-2.1 using the NeMo AutoModel full-SFT recipe configured for two nodes, eight GPUs per node, FSDP2, and EP16.
- [Laguna-XS-2.1](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/poolside/Laguna-XS-2.1.md): Use NeMo AutoModel to fine-tune Laguna-XS-2.1 for LLM workflows with checked-in text generation recipes and documented distributed settings.