NVIDIA: Nemotron 3 Nano Omni (free)

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs…

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.

Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.

Specifications & capabilities

Input
text, audio, image, video
Output
text
Context window · tokens
256000
Published model ID
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Capabilities
audioInput, multimodal, reasoning, toolCalling, transcription, visionInput
Description source ↗

Evaluations

1–2 / 2

Published prices

1–2 / 2

Provider specifications & access

1–4 / 4

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 ↗

source model id
HuggingFace/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-bf16@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
nvidia-open-model-agreement
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 ↗

    source model id
    HuggingFace/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-bf16@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    nvidia-open-model-agreement
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 ↗

      source model id
      HuggingFace/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-bf16@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      nvidia-open-model-agreement
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        nemotron-3-nano-omni-30b-a3b-reasoning ↗

        source model id
        nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
        hosting
        nvidia-catalog
        platforms
        • NVIDIA Build / NIM
        context length
        262144
        architecture
        input_modalities
        • video
        • audio
        • image
        • text
        output_modalities
        • text
        capabilities
        • transcription
        • toolCalling
        • reasoning

        Source specification observations

        1–3 / 3

        nvidiaNim ↗

        field
        context_length
        value
        262144
        normalized value
        262144
        scope
        source-model
        source id
        nvidiaNim
        confidence
        1

        openRouter ↗

        field
        context_length
        value
        256000
        normalized value
        256000
        scope
        source-model
        source id
        openRouter
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        65536
        normalized value
        65536
        scope
        source-model
        source id
        openRouter
        confidence
        1

        Original sources

        1–12 / 12

        Hugging Face · nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 ↗

        Microsoft Foundry · Model page ↗

        Microsoft Foundry · Model page ↗

        Microsoft Foundry · Model page ↗

        NVIDIA · Model page ↗

        OpenRouter · Model page ↗

        Microsoft Foundry · Model documentation ↗

        NVIDIA · Documentation ↗

        Hugging Face · Catalog ↗

        Microsoft Foundry · Catalog ↗

        NVIDIA · Catalog ↗

        OpenRouter · Catalog ↗

        Source links

        1–6 / 6

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

        Install TensorTrace