{
  "slug": "mistral-large-4",
  "order": 117,
  "name": "Mistral Large 4 (1T)",
  "baseTitle": "Mistral Large 4",
  "company": "Mistral AI",
  "country": "France",
  "flag": "🇫🇷",
  "date": "2026-10-29",
  "decoderType": "Sparse MoE",
  "attention": "MLA with modified DeepSeek Sparse Attention, index reuse, and KV sharing",
  "layerMix": "72 MLA/DSA",
  "scale": "1T total, 52B active (5.2% active)",
  "totalParams": 1000000000000,
  "activeParams": 52000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "Mistral Ecosystem Open-Weight License",
  "kvCacheText": "80.75 KiB",
  "kvCacheKiB": 80.75,
  "kvCacheLevel": "Moderate",
  "summary": "Mistral's trillion-parameter multimodal MoE combines MLA with sparse token selection and cross-layer KV sharing.",
  "keyDetail": "Selects the top 2,048 tokens, reuses sparse indices across layers, and alternates three LeRoPE layers with one NoPE layer.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/mistral-large-4.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/mistral-large-4.webp",
    "alt": "Figure 1: Mistral Large 4",
    "width": 960,
    "height": 833
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B/blob/main/config.json",
      "title": "mistralai/Mistral-Large-4-1T-A52B"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B/blob/main/assets/technical_report.pdf",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "mla",
      "label": "MLA",
      "name": "Multi-Head Latent Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mla/"
    },
    {
      "slug": "deepseek-sparse-attention",
      "label": "DSA",
      "name": "DeepSeek Sparse Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/deepseek-sparse-attention/"
    },
    {
      "slug": "indexshare",
      "label": "IndexShare",
      "name": "IndexShare",
      "url": "https://llm-atlas-7or.pages.dev/concepts/indexshare/"
    },
    {
      "slug": "kv-sharing",
      "label": "KV Sharing",
      "name": "Cross-Layer KV Sharing",
      "url": "https://llm-atlas-7or.pages.dev/concepts/kv-sharing/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "nope",
      "label": "NoPE",
      "name": "No Positional Embeddings",
      "url": "https://llm-atlas-7or.pages.dev/concepts/nope/"
    }
  ],
  "aai": {
    "v5": {
      "label": "AA Intelligence Index v5.0",
      "total": 26,
      "profile": {
        "Knowledge Work": 40.6,
        "Coding": 18.9,
        "Science": 13,
        "General": 31.7
      },
      "url": "https://artificialanalysis.ai/models/mistral-large-4"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-mistral-large-4",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/mistral-large-4/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/mistral-large-4.md"
}