gemma-3-4b-it | NVIDIA NeMo AutoModel

gemma-3-4b-it is a multimodal Gemma 3 checkpoint for image-text inputs. NeMo AutoModel provides full-parameter and Low-Rank Adaptation (LoRA) recipes for supervised fine-tuning.

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

Fine-Tune gemma-3-4b-it

From the repository root, run:

uv run automodel examples/vlm_finetune/gemma3/gemma3_vl_4b_cord_v2.yaml --nproc-per-node 8

Choose a Workflow

Goal	Start Here
Fine-tune on CORD-v2	Use gemma3_vl_4b_cord_v2.yaml.
Fine-tune with LoRA	Use gemma3_vl_4b_cord_v2_peft.yaml.
Fine-tune with Megatron FSDP	Use gemma3_vl_4b_cord_v2_megatron_fsdp.yaml.
Fine-tune on MedPix-VQA	Use gemma3_vl_4b_medpix.yaml.

Model Reference

Model Architecture

Property	Value
Task	Image-text-to-text
Hugging Face Architecture	`Gemma3ForConditionalGeneration`
Checkpoint	`google/gemma-3-4b-it`

Gemma 3 and Gemma 3n Fine-Tuning Guide

Fine-Tune gemma-3-4b-it

Choose a Workflow

Model Reference

Model Architecture

Related Resources