{
  "slug": "nemotron-3-5-super-vl-120b-a12b",
  "order": 111,
  "name": "Nemotron 3.5 Super VL (120B-A12B)",
  "baseTitle": "Nemotron 3.5 Super VL 120B-A12B",
  "company": "NVIDIA",
  "country": "United States",
  "flag": "🇺🇸",
  "date": "2026-10-15",
  "decoderType": "Hybrid MoE",
  "attention": "Mostly Mamba-2 with eight GQA layers",
  "layerMix": "8 GQA + 40 Mamba-2 + 40 LatentMoE; GQA + MoE MTP predictor",
  "scale": "120B total, 12B active (10% active)",
  "totalParams": 120000000000,
  "activeParams": 12000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "OpenMDW 1.1",
  "kvCacheText": "8 KiB",
  "kvCacheKiB": 8,
  "kvCacheLevel": "Very low",
  "summary": "NVIDIA's vision-language model extends the Nemotron 3 Super backbone with C-RADIO vision encoding and shared-weight multi-token prediction. The figure shows the language backbone, with the vision encoder and MTP omitted.",
  "keyDetail": "Routes each token to 22 of 512 experts in a 1,024-dimensional latent space, alongside one shared expert at the full 4,096-dimensional width.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/nemotron-3-5-super-vl-120b-a12b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/nemotron-3-5-super-vl-120b-a12b.webp",
    "alt": "Figure 1: Nemotron 3.5 Super VL 120B-A12B",
    "width": 954,
    "height": 960
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4/blob/main/config.json",
      "title": "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4"
    },
    {
      "label": "License",
      "href": "https://openmdw.ai/license/1-1/",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "latent-moe",
      "label": "LatentMoE",
      "name": "Latent MoE",
      "url": "https://llm-atlas-7or.pages.dev/concepts/latent-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": {
    "v5": {
      "label": "AA Intelligence Index v5.0",
      "total": 13.6,
      "profile": {
        "Knowledge Work": 19.5,
        "Coding": 3.7,
        "Science": 5.4,
        "General": 25.9
      },
      "url": "https://artificialanalysis.ai/models/nemotron-3-5-super-vl"
    },
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 26.5,
      "profile": {
        "General": 32.6,
        "Scientific": 20.6,
        "Coding": 23.9,
        "Agents": 26
      },
      "url": "https://artificialanalysis.ai/models/nemotron-3-5-super-vl"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-nemotron-3-5-super-vl-120b-a12b",
  "family": "hybrid-moe",
  "url": "https://llm-atlas-7or.pages.dev/models/nemotron-3-5-super-vl-120b-a12b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/nemotron-3-5-super-vl-120b-a12b.md"
}