> 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/thudm/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Z.ai

> Browse NeMo AutoModel coverage for Z.ai large language models.

* [`chatglm3-6b`](/model-coverage/large-language-models/thudm/chatglm3-6b)
* [`glm-4-9b-chat-hf`](/model-coverage/large-language-models/thudm/glm-4-9b-chat-hf)
* [`GLM-4.5-Air`](/model-coverage/large-language-models/thudm/GLM-4.5-Air)
* [`GLM-4.7`](/model-coverage/large-language-models/thudm/GLM-4.7)
* [`GLM-5`](/model-coverage/large-language-models/thudm/GLM-5)
* [`GLM-5.1`](/model-coverage/large-language-models/thudm/GLM-5.1)
* [`GLM-5.2`](/model-coverage/large-language-models/thudm/GLM-5.2)
* [`GLM-5.3`](/model-coverage/large-language-models/thudm/GLM-5.3)

> Browse NeMo AutoModel coverage for Z.ai large language models.

## Docs

- [chatglm3-6b](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/chatglm3-6b.md): Reference chatglm3-6b checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [glm-4-9b-chat-hf](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/glm-4-9b-chat-hf.md): Use glm-4-9b-chat-hf with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [GLM-4.5-Air](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-4.5-Air.md): Use GLM-4.5-Air with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [GLM-4.7](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-4.7.md): Use NeMo AutoModel to fine-tune GLM-4.7 for LLM workflows with checked-in text generation recipes and documented distributed settings.
- [GLM-5](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-5.md): Fine-tune GLM-5 through GLM-5.3 mixture-of-experts checkpoints with NeMo AutoModel using checked-in MLA and DSA recipes.
- [GLM-5.1](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-5.1.md): Use NeMo AutoModel to fine-tune GLM-5.1 for LLM workflows with checked-in text generation recipes and documented distributed settings.
- [GLM-5.2](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-5.2.md): Use NeMo AutoModel to fine-tune GLM-5.2 for LLM workflows with checked-in text generation recipes and documented distributed settings.
- [GLM-5.3](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/large-language-models/thudm/GLM-5.3.md): Use NeMo AutoModel to fine-tune GLM-5.3 for LLM workflows with checked-in text generation recipes and documented distributed settings.