{
  "slug": "nemotron-3-5-lightning-30b-a3b",
  "order": 96,
  "name": "Nemotron 3.5 Lightning (30B-A3B)",
  "baseTitle": "Nemotron 3.5 Lightning 30B-A3B",
  "company": "NVIDIA",
  "country": "United States",
  "flag": "🇺🇸",
  "date": "2026-08-11",
  "decoderType": "Hybrid MoE",
  "attention": "Mostly Mamba-2 with six GQA layers",
  "layerMix": "6 GQA + 23 Mamba-2 + 23 MoE; GQA + MoE MTP predictor",
  "scale": "30B total, 3B active (10% active)",
  "totalParams": 30000000000,
  "activeParams": 3000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "OpenMDW 1.1",
  "kvCacheText": "6 KiB",
  "kvCacheKiB": 6,
  "kvCacheLevel": "Very low",
  "summary": "NVIDIA's 30B hybrid model keeps 3B parameters active and extends the Nemotron 3 Nano backbone with a 1M-token context window and multi-token prediction.",
  "keyDetail": "Adds a shared GQA-plus-MoE MTP predictor to the 52-layer Nemotron 3 Nano backbone.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/nemotron-3-5-lightning-30b-a3b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/nemotron-3-5-lightning-30b-a3b.webp",
    "alt": "Figure 1: Nemotron 3.5 Lightning 30B-A3B",
    "width": 937,
    "height": 960
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4/blob/main/config.json",
      "title": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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": "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": 5.5,
      "profile": {
        "Knowledge Work": 1,
        "Coding": 0.2,
        "Science": 0.6,
        "General": 20.6
      },
      "url": "https://artificialanalysis.ai/models/nemotron-3-5-lightning"
    },
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 12.9,
      "profile": {
        "General": 26.3,
        "Scientific": 5.3,
        "Coding": 16.3,
        "Agents": 2.6
      },
      "url": "https://artificialanalysis.ai/models/nemotron-3-5-lightning"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-nemotron-3-5-lightning-30b-a3b",
  "family": "hybrid-moe",
  "url": "https://llm-atlas-7or.pages.dev/models/nemotron-3-5-lightning-30b-a3b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/nemotron-3-5-lightning-30b-a3b.md"
}