{
  "slug": "nemotron-3-super-120b-a12b",
  "order": 34,
  "name": "Nemotron 3 Super (120B-A12B)",
  "baseTitle": "Nemotron 3 Super 120B-A12B",
  "company": "NVIDIA",
  "country": "United States",
  "flag": "🇺🇸",
  "date": "2026-03-11",
  "decoderType": "Hybrid MoE",
  "attention": "Mostly Mamba-2 with a few GQA layers",
  "layerMix": "8 GQA + 40 Mamba-2 + 40 MoE",
  "scale": "120B total, 12B active (10% active)",
  "totalParams": 120000000000,
  "activeParams": 12000000000,
  "context": "1,000,000",
  "contextTokens": 1000000,
  "license": "NVIDIA Nemotron Open Model License",
  "kvCacheText": "8 KiB",
  "kvCacheKiB": 8,
  "kvCacheLevel": "Very low",
  "summary": "The Super variant scales up Nano and adds both latent experts and native speculative decoding support.",
  "keyDetail": "Adds latent-space MoE and shared-weight MTP for fast inference.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/nemotron-3-super-120b-a12b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/nemotron-3-super-120b-a12b.webp",
    "alt": "Figure 51.3: Nemotron 3 Super 120B-A12B",
    "width": 941,
    "height": 960
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A7182-nemotron-3-super",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A7182-nemotron-3-super",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/blob/main/config.json",
      "title": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
    },
    {
      "label": "License",
      "href": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "latent-moe",
      "label": "LatentMoE",
      "name": "Latent MoE",
      "url": "https://llm-atlas-7or.pages.dev/concepts/latent-moe/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "hybrid-attention",
      "label": "Hybrid Attention",
      "name": "Hybrid Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/hybrid-attention/"
    },
    {
      "slug": "mtp",
      "label": "MTP",
      "name": "Multi-Token Prediction",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mtp/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 12.8,
      "profile": {
        "General": 22.1,
        "Scientific": 12,
        "Coding": 18.1,
        "Agents": 0.6
      },
      "url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-nemotron-3-super-120b-a12b",
  "family": "hybrid-moe",
  "url": "https://llm-atlas-7or.pages.dev/models/nemotron-3-super-120b-a12b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/nemotron-3-super-120b-a12b.md"
}