Qwen3-32B | NVIDIA NeMo AutoModel

Qwen3-32B has a checked-in NeMo AutoModel recipe for text generation. The Hugging Face configuration declares the Qwen3ForCausalLM architecture.

Fine-Tune Qwen3-32B

Follow the installation instructions, then run the recipe from the repository root:

automodel examples/llm_finetune/qwen/qwen3_32b_tulu3.yaml --nproc-per-node 8

Goal	Start Here
Run the primary recipe for this model	Use the recipe configuration.
Try another checked-in recipe for this model	Use the alternate recipe.

Setting	Configuration
Hardware	-
Strategy	FSDP2; tp_size=1, pp_size=1, cp_size=1
Nodes	1
Features	Activation checkpointing (activation_checkpointing=true)
Advanced	sequence length 2048

Property	Value
Task	Text generation
Architecture	`Qwen3ForCausalLM`