Model CoverageOmni Models

Nemotron-3-Nano-Omni

View as Markdown

Nemotron-3-Nano-Omni-30B-A3B-Reasoning is NVIDIA’s omnimodal reasoning model. It pairs a NemotronH (hybrid Mamba-2 + Attention) MoE language backbone with a RADIO v2.5-H vision encoder and a Parakeet (FastConformer) sound encoder, supporting interleaved text, image, and audio inputs.

TaskOmnimodal (Text·Image·Audio)
ArchitectureNemotronH_Nano_Omni_Reasoning_V3
Parameters30B total / 3B active
HF Orgnvidia

Available Models

  • Nemotron-3-Nano-Omni-30B-A3B-Reasoning: 30B total, 3B activated (MoE)

Architecture

  • NemotronH_Nano_Omni_Reasoning_V3

Example Recipes

RecipeDatasetDescription
nemotron_omni_cord_v2.yamlCORD-v2Full SFT — receipt parsing
nemotron_omni_cord_v2_peft.yamlCORD-v2LoRA PEFT — receipt parsing

Try with NeMo AutoModel

1. Install (NeMo AutoModel):

$pip install nemo-automodel

2. Clone the repo to get the example recipes:

$git clone https://github.com/NVIDIA-NeMo/Automodel.git
$cd Automodel

3. Run the recipe from inside the repo (8x H100 example):

$automodel examples/vlm_finetune/nemotron_omni/nemotron_omni_cord_v2.yaml --nproc-per-node 8

For a full walkthrough — dataset preparation, SFT vs. LoRA configs, and post-training inference — see the Nemotron-Omni guide.