{
  "slug": "qwen3-4b",
  "order": 13,
  "name": "Qwen3 (4B)",
  "baseTitle": "Qwen3 4B",
  "company": "Alibaba Cloud",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2025-04-28",
  "decoderType": "Dense",
  "attention": "GQA with QK-Norm",
  "layerMix": "36 GQA",
  "scale": "4B parameters",
  "totalParams": 4000000000,
  "activeParams": 4000000000,
  "context": "32,768",
  "contextTokens": 32768,
  "license": "Apache License 2.0",
  "kvCacheText": "144 KiB",
  "kvCacheKiB": 144,
  "kvCacheLevel": "Moderate",
  "summary": "Mid-size dense Qwen3 model used here as a clean baseline against SmolLM3 and Tiny Aya.",
  "keyDetail": "Compact Qwen3 dense stack with QK-Norm and a 151k vocabulary.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/qwen3-4b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/qwen3-4b.webp",
    "alt": "Figure 21: Qwen3 4B",
    "width": 912,
    "height": 960
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A77-smollm3",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A77-smollm3",
      "title": null
    },
    {
      "label": "From scratch",
      "href": "https://github.com/rasbt/LLMs-from-scratch/tree/main/ch05/11_qwen3",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/Qwen/Qwen3-4B/blob/main/config.json",
      "title": "Qwen/Qwen3-4B"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2505.09388",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "qk-norm",
      "label": "QK-Norm",
      "name": "QK-Norm",
      "url": "https://llm-atlas-7or.pages.dev/concepts/qk-norm/"
    },
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 6.6,
      "profile": {},
      "url": "https://artificialanalysis.ai/models/qwen3-4b-instruct"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-qwen3-4b",
  "family": "dense",
  "url": "https://llm-atlas-7or.pages.dev/models/qwen3-4b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/qwen3-4b.md"
}