GLM-4.5-Air | NVIDIA NeMo AutoModel

GLM-4.5 and GLM-4.7 are Mixture-of-Experts variants of the GLM family released under the zai-org HuggingFace organization. GLM-4.7-Flash is a lighter variant with fewer active parameters.

Set up NeMo AutoModel with the latest container or follow the installation instructions.

Fine-Tune GLM-4.5-Air

This recipe was validated on 8 nodes x 8 GPUs (64 H100s). See the Launcher Guide for multi-node setup.

From the repository root, run:

uv run automodel --nproc-per-node=8 examples/llm_finetune/glm/glm_4.5_air_te_deepep.yaml

Choose a Workflow

Goal	Start Here
Supervised fine-tuning (SFT) - GLM-4.5-Air with TE + DeepEP	Use glm_4.5_air_te_deepep.yaml.

Model Reference

Model Architecture

Property	Value
Task	Text Generation (MoE)
Architecture	`Glm4MoeForCausalLM` / `Glm4MoeLiteForCausalLM`
Parameters	106B total / 12B active
Hugging Face Organization	zai-org

Glm4MoeForCausalLM - GLM-4.5, GLM-4.7
Glm4MoeLiteForCausalLM - GLM-4.7-Flash

Available Models

Model	HF ID
GLM-4.5-Air	`zai-org/GLM-4.5-Air`

LLM Fine-Tuning Guide
Large MoE Fine-Tuning Guide