{
  "slug": "qwen3-6-35b-a3b",
  "order": 65,
  "name": "Qwen3.6 (35B-A3B)",
  "baseTitle": "Qwen3.6 35B-A3B",
  "company": "Alibaba Cloud",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-04-15",
  "decoderType": "Sparse hybrid",
  "attention": "3:1 Gated DeltaNet and Gated Attention",
  "layerMix": "10 gated attention + 30 DeltaNet",
  "scale": "35B total, 3B active (8.6% active)",
  "totalParams": 35000000000,
  "activeParams": 3000000000,
  "context": "262,144",
  "contextTokens": 262144,
  "license": "Apache License 2.0",
  "kvCacheText": "20 KiB",
  "kvCacheKiB": 20,
  "kvCacheLevel": "Very low",
  "summary": "Compact Qwen3.6 open-weight MoE that keeps the Qwen3.5 hybrid Gated DeltaNet/Gated Attention recipe while activating only about 3B parameters.",
  "keyDetail": "Uses 256 experts with 8 routed plus 1 shared expert active inside a 40-layer hybrid stack.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/qwen3-6-35b-a3b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/qwen3-6-35b-a3b.webp",
    "alt": "Figure 1: Qwen3.6 35B-A3B",
    "width": 960,
    "height": 904
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/config.json",
      "title": "Qwen/Qwen3.6-35B-A3B"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://qwen.ai/blog?id=qwen3.6-35b-a3b",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "gated-attention",
      "label": "Gated Attention",
      "name": "Gated Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gated-attention/"
    },
    {
      "slug": "hybrid-attention",
      "label": "Hybrid Attention",
      "name": "Hybrid Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/hybrid-attention/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 18.2,
      "profile": {
        "General": 28.7,
        "Scientific": 11.3,
        "Coding": 18.3,
        "Agents": 12.7
      },
      "url": "https://artificialanalysis.ai/models/qwen3-6-35b-a3b"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-qwen3-6-35b-a3b",
  "family": "hybrid-moe",
  "url": "https://llm-atlas-7or.pages.dev/models/qwen3-6-35b-a3b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/qwen3-6-35b-a3b.md"
}