gemma-4-31B-it | NVIDIA NeMo AutoModel

gemma-4-31B-it is a multimodal Gemma 4 checkpoint for image-text inputs. NeMo AutoModel provides full-parameter and Low-Rank Adaptation (LoRA) recipes, including tensor-parallel and pipeline-parallel variants.

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

Fine-Tune gemma-4-31B-it

From the repository root, run the 8-GPU recipe:

uv run automodel examples/vlm_finetune/gemma4/gemma4_31b.yaml --nproc-per-node 8

Choose a Workflow

Goal	Start Here
Fine-tune on MedPix-VQA	Use gemma4_31b.yaml.
Fine-tune with LoRA	Use gemma4_31b_peft.yaml.
Fine-tune with tensor parallelism	Use gemma4_31b_tp4.yaml.
Fine-tune with tensor and pipeline parallelism	Use gemma4_31b_tp4_pp2.yaml or the multi-node PP4 recipe.

Model Reference

Model Architecture

Property	Value
Task	Image-text-to-text
Hugging Face Architecture	`Gemma4ForConditionalGeneration`
Checkpoint	`google/gemma-4-31B-it`

Gemma 4 Fine-Tuning Guide

Fine-Tune gemma-4-31B-it

Choose a Workflow

Model Reference

Model Architecture

Related Resources