> 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.

# Phi-3-small-8k-instruct

> Reference Phi-3-small-8k-instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.

[Phi-3-Small](https://azure.microsoft.com/en-us/products/phi) is Microsoft's 7B model using a distinct `Phi3SmallForCausalLM` architecture with blocksparse attention, separate from the standard Phi-3 family.

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                      | Text Generation                               |
| Architecture              | `Phi3SmallForCausalLM`                        |
| Parameters                | 7B                                            |
| Hugging Face Organization | [microsoft](https://huggingface.co/microsoft) |

### Available Models

| Model                   | HF ID                                                                                           |
| ----------------------- | ----------------------------------------------------------------------------------------------- |
| Phi-3-small-8k-instruct | [`microsoft/Phi-3-small-8k-instruct`](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)