{
  "slug": "xiaomi-mimo-v2-6-pro-rl-1-02t",
  "order": 105,
  "name": "Xiaomi MiMo-V2.6-Pro-RL (1.02T)",
  "baseTitle": "Xiaomi MiMo-V2.6-Pro-RL 1.02T",
  "company": "Xiaomi",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-09-21",
  "decoderType": "Sparse omnimodal MoE",
  "attention": "GQA with 6:1 sliding-window/global attention",
  "layerMix": "60 sliding-window + 10 global",
  "scale": "1.02T total, 42B active (4.1% active)",
  "totalParams": 1020000000000,
  "activeParams": 42000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "MIT License",
  "kvCacheText": "350 KiB",
  "kvCacheKiB": 350,
  "kvCacheLevel": "Very high",
  "summary": "Omnimodal sparse MoE model with the MiMo-V2.5-Pro text backbone, mixed-domain reinforcement learning, and a five-layer DFlash speculative decoder.",
  "keyDetail": "Uses 384 routed experts with top-8 routing, one dense prefix layer, no shared experts, and a 128-token sliding window.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/mimo-2.6-pro.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/mimo-2.6-pro.webp",
    "alt": "Figure 1: Xiaomi MiMo-V2.6-Pro-RL 1.02T",
    "width": 960,
    "height": 949
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/config.json",
      "title": "XiaomiMiMo/MiMo-V2.6-Pro-RL"
    },
    {
      "label": "Tech report",
      "href": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/resolve/main/MiMo_V2_6_technical_report.pdf",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "swa",
      "label": "SWA",
      "name": "Sliding Window Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/swa/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "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": 29.9,
      "profile": {
        "Knowledge Work": 45.9,
        "Coding": 28.3,
        "Science": 17,
        "General": 28
      },
      "url": "https://artificialanalysis.ai/models/mimo-v2-6-pro"
    },
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 46.3,
      "profile": {
        "General": 42.3,
        "Scientific": 38,
        "Coding": 47.9,
        "Agents": 54.9
      },
      "url": "https://artificialanalysis.ai/models/mimo-v2-6-pro"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-xiaomi-mimo-v2-6-pro-rl-1-02t",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/xiaomi-mimo-v2-6-pro-rl-1-02t/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/xiaomi-mimo-v2-6-pro-rl-1-02t.md"
}