> 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.

# chatglm3-6b

> Reference chatglm3-6b checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.

[ChatGLM](https://github.com/zai-org/ChatGLM-6B) is a bilingual (Chinese-English) conversational language model from Zhipu AI. ChatGLM2 and ChatGLM3 extend the original with improved performance, longer context, and more efficient attention.

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              | `ChatGLMModel`                            |
| Parameters                | 6B                                        |
| Hugging Face Organization | [zai-org](https://huggingface.co/zai-org) |

* `ChatGLMModel` / `ChatGLMForConditionalGeneration`

### Available Models

| Model       | HF ID                                                               |
| ----------- | ------------------------------------------------------------------- |
| ChatGLM3 6B | [`zai-org/chatglm3-6b`](https://huggingface.co/zai-org/chatglm3-6b) |

## Related Resources

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