DeepSeek V4 Pro is Live → Try it now.

Model Library
/NVIDIA/NVIDIA Nemotron 3 Nano Omni 30B A3B
NVIDIA icon

NVIDIA Nemotron 3 Nano Omni 30B A3B

Ready
accounts/fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b

    NVIDIA Nemotron 3 Nano Omni is an open multimodal model from NVIDIA for reasoning across text, images, video, and audio. Built on a hybrid Mixture-of-Experts architecture with 30B total / 3B active parameters. Reasoning is currently supported for text and image inputs only; pass enable_thinking: false in chat_template_kwargs for video and audio requests.

    NVIDIA Nemotron 3 Nano Omni 30B A3B API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use NVIDIA Nemotron 3 Nano Omni 30B A3B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    4/27/2026
    Kind
    Base model
    Provider
    NVIDIA

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    30B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    262k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported