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

# Microsoft

> Browse NeMo AutoModel coverage for Microsoft large language models.

* [`phi-2`](/model-coverage/large-language-models/microsoft/phi-2)
* [`Phi-3-mini-4k-instruct`](/model-coverage/large-language-models/microsoft/Phi-3-mini-4k-instruct)
* [`Phi-3-small-8k-instruct`](/model-coverage/large-language-models/microsoft/Phi-3-small-8k-instruct)
* [`Phi-4`](/model-coverage/large-language-models/microsoft/Phi-4)

> Browse NeMo AutoModel coverage for Microsoft large language models.

## Docs

- [phi-2](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/microsoft/phi-2.md): Use phi-2 with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [Phi-3-mini-4k-instruct](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/microsoft/Phi-3-mini-4k-instruct.md): Use NeMo AutoModel to fine-tune Phi-3-mini-4k-instruct for LLM workflows with checked-in text generation recipes and documented distributed settings.
- [Phi-3-small-8k-instruct](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/microsoft/Phi-3-small-8k-instruct.md): Reference Phi-3-small-8k-instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Phi-4](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/microsoft/Phi-4.md): Use Phi-4 with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.