{
  "slug": "gemma-3-270m",
  "order": 20,
  "name": "Gemma 3 (270M)",
  "baseTitle": "Gemma 3 270M",
  "company": "Google",
  "country": "United States",
  "flag": "🇺🇸",
  "date": "2025-08-14",
  "decoderType": "Dense",
  "attention": "Multi-query attention with QK-Norm and 5:1 sliding-window/global attention",
  "layerMix": "15 sliding-window + 3 global",
  "scale": "270M parameters",
  "totalParams": 270000000,
  "activeParams": 270000000,
  "context": "128,000",
  "contextTokens": 128000,
  "license": "Gemma Terms of Use + Gemma Prohibited Use Policy",
  "kvCacheText": "18 KiB",
  "kvCacheKiB": 18,
  "kvCacheLevel": "Very low",
  "summary": "Tiny Gemma 3 variant that preserves the family's local-global attention recipe at a toy scale.",
  "keyDetail": "Keeps the Gemma 3 stack shape while shrinking down to 4 attention heads, a single KV head, and the same 262k vocabulary.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/gemma-3-270m.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/gemma-3-270m.webp",
    "alt": "Figure 16: Gemma 3 270M",
    "width": 960,
    "height": 955
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A74-mistral-small-31",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A74-mistral-small-31",
      "title": null
    },
    {
      "label": "From scratch",
      "href": "https://github.com/rasbt/LLMs-from-scratch/tree/main/ch05/12_gemma3",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/google/gemma-3-270m/blob/main/config.json",
      "title": "google/gemma-3-270m"
    },
    {
      "label": "License",
      "href": "https://ai.google.dev/gemma/prohibited_use_policy",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2503.19786",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "qk-norm",
      "label": "QK-Norm",
      "name": "QK-Norm",
      "url": "https://llm-atlas-7or.pages.dev/concepts/qk-norm/"
    },
    {
      "slug": "swa",
      "label": "SWA",
      "name": "Sliding Window Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/swa/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 5.1,
      "profile": {
        "Scientific": 1.8
      },
      "url": "https://artificialanalysis.ai/models/gemma-3-270m"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-gemma-3-270m",
  "family": "dense",
  "url": "https://llm-atlas-7or.pages.dev/models/gemma-3-270m/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/gemma-3-270m.md"
}