{
  "slug": "naive-n0-5-flash-309b",
  "order": 107,
  "name": "Naive-N0.5-Flash (309B)",
  "baseTitle": "Naive-N0.5-Flash 309B",
  "company": "NaiveAI",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-09-27",
  "decoderType": "Sparse MoE",
  "attention": "GQA with sliding-window attention and DeepSeek Sparse Attention",
  "layerMix": "39 sliding-window + 9 GQA/DSA",
  "scale": "309B total, 15.5B active (5.0% active)",
  "totalParams": 309000000000,
  "activeParams": 15500000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "MIT License",
  "kvCacheText": "219.75 KiB",
  "kvCacheKiB": 219.75,
  "kvCacheLevel": "High",
  "summary": "MiMo-V2.5-derived sparse MoE that replaces its global attention layers with GQA-based DeepSeek Sparse Attention for a native 1M-token context.",
  "keyDetail": "Pairs a 128-token local window with top-2,048 DSA selection, four DSA KV heads, and a 16-head indexer. Uses 256 routed experts with top-8 routing and no full-attention layers.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/naive-n0-5-flash-309b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/naive-n0-5-flash-309b.webp",
    "alt": "Figure 1: Naive-N0.5-Flash 309B",
    "width": 960,
    "height": 935
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/NaiveAI/Naive-N0.5-Flash/blob/main/config.json",
      "title": "NaiveAI/Naive-N0.5-Flash"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/NaiveAI/Naive-N0.5-Flash/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://naive.ai/en/research/",
      "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": "deepseek-sparse-attention",
      "label": "DSA",
      "name": "DeepSeek Sparse Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/deepseek-sparse-attention/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    }
  ],
  "aai": null,
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-naive-n0-5-flash-309b",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/naive-n0-5-flash-309b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/naive-n0-5-flash-309b.md"
}