{
  "slug": "qwen3-8b",
  "order": 14,
  "name": "Qwen3 (8B)",
  "baseTitle": "Qwen3 8B",
  "company": "Alibaba Cloud",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2025-04-28",
  "decoderType": "Dense",
  "attention": "GQA with QK-Norm",
  "layerMix": "36 GQA",
  "scale": "8B parameters",
  "totalParams": 8000000000,
  "activeParams": 8000000000,
  "context": "128,000",
  "contextTokens": 128000,
  "license": "Apache License 2.0",
  "kvCacheText": "144 KiB",
  "kvCacheKiB": 144,
  "kvCacheLevel": "Moderate",
  "summary": "Dense Qwen3 baseline used here to show how little OLMo 3 changed the overall decoder recipe.",
  "keyDetail": "Reference Qwen3 dense stack with QK-Norm and 8 KV heads.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/qwen3-8b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/qwen3-8b.webp",
    "alt": "Figure 44: Qwen3 8B",
    "width": 916,
    "height": 960
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A715-olmo-3-thinking",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A715-olmo-3-thinking",
      "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/Qwen3-8B/blob/main/config.json",
      "title": "Qwen/Qwen3-8B"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/Qwen/Qwen3-8B/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,
      "profile": {
        "Scientific": 1
      },
      "url": "https://artificialanalysis.ai/models/qwen3-8b-instruct"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-qwen3-8b",
  "family": "dense",
  "url": "https://llm-atlas-7or.pages.dev/models/qwen3-8b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/qwen3-8b.md"
}