> 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.

# Minitron-8B-Base

> Reference Minitron-8B-Base checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.

[NVIDIA Nemotron](https://www.nvidia.com/en-us/ai-data-science/foundation-models/) and [Minitron](https://developer.nvidia.com/blog/how-to-prune-and-distill-llama-3-1-8b-to-an-nvidia-llama-3-1-minitron-4b-model/) are NVIDIA's family of language models. Minitron models are produced by pruning and distilling larger Llama/Nemotron models into compact, high-performance checkpoints.

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              | `NemotronForCausalLM`                   |
| Parameters                | 8B                                      |
| Hugging Face Organization | [nvidia](https://huggingface.co/nvidia) |

### Available Models

| Model            | HF ID                                                                       |
| ---------------- | --------------------------------------------------------------------------- |
| Minitron 8B Base | [`nvidia/Minitron-8B-Base`](https://huggingface.co/nvidia/Minitron-8B-Base) |

## Related Resources

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