{
  "slug": "minimax-m3-1-flash-428b",
  "order": 115,
  "name": "MiniMax M3.1-Flash (428B)",
  "baseTitle": "MiniMax M3.1-Flash 428B",
  "company": "MiniMax",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-10-19",
  "decoderType": "Sparse MoE",
  "attention": "GQA with QK-Norm and MiniMax Sparse Attention",
  "layerMix": "60 MiniMax Sparse Attention; 3 dense FFN + 57 MoE",
  "scale": "428B total, 23B active (5.4% active)",
  "totalParams": 428000000000,
  "activeParams": 23000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "MiniMax Community License",
  "kvCacheText": "120 KiB",
  "kvCacheKiB": 120,
  "kvCacheLevel": "Moderate",
  "summary": "MiniMax M3 successor with sparse attention in all 60 decoder layers, quantization-aware training, and a DSpark draft head for speculative decoding.",
  "keyDetail": "All 60 layers use sparse attention; the first 3 retain dense FFNs, while the remaining 57 route to 4 of 128 experts plus 1 shared expert per token.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/minimax-m3.1-flash.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/minimax-m3.1-flash.webp",
    "alt": "Figure 1: MiniMax M3.1-Flash 428B",
    "width": 936,
    "height": 960
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/blob/main/config.json",
      "title": "MiniMaxAI/MiniMax-M3.1-Flash"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/abs/2606.13392",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "qk-norm",
      "label": "QK-Norm",
      "name": "QK-Norm",
      "url": "https://llm-atlas-7or.pages.dev/concepts/qk-norm/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    }
  ],
  "aai": {
    "v5": {
      "label": "AA Intelligence Index v5.0",
      "total": 28.9,
      "profile": {
        "Knowledge Work": 47.9,
        "Coding": 22.8,
        "Science": 14.4,
        "General": 30.5
      },
      "url": "https://artificialanalysis.ai/models/minimax-m3-1-flash"
    },
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 42.7,
      "profile": {
        "General": 40.1,
        "Scientific": 35.1,
        "Coding": 39.6,
        "Agents": 52.4
      },
      "url": "https://artificialanalysis.ai/models/minimax-m3-1-flash"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-minimax-m3-1-flash-428b",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/minimax-m3-1-flash-428b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/minimax-m3-1-flash-428b.md"
}