{
  "slug": "glm-4-5-air",
  "order": 51,
  "name": "GLM-4.5-Air (106B)",
  "baseTitle": "GLM-4.5-Air",
  "company": "Z.ai",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2025-07-28",
  "decoderType": "Sparse MoE",
  "attention": "GQA",
  "layerMix": "46 GQA",
  "scale": "106B total, 12B active (11.3% active)",
  "totalParams": 106000000000,
  "activeParams": 12000000000,
  "context": "128,000",
  "contextTokens": 128000,
  "license": "MIT License",
  "kvCacheText": "184 KiB",
  "kvCacheKiB": 184,
  "kvCacheLevel": "High",
  "summary": "Compact GLM-4.5 companion that keeps the same agent-oriented sparse MoE recipe at a smaller serving footprint.",
  "keyDetail": "Shrinks the GLM-4.5 layout to 46 layers, keeps the dense warmup, and inherits the MTP training recipe.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/glm-4-5-air.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/glm-4-5-air.webp",
    "alt": "Figure 1: GLM-4.5-Air",
    "width": 960,
    "height": 936
  },
  "articleUrl": null,
  "links": [
    {
      "label": "config.json",
      "href": "https://huggingface.co/zai-org/GLM-4.5-Air/blob/main/config.json",
      "title": "zai-org/GLM-4.5-Air"
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2508.06471",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "mtp",
      "label": "MTP",
      "name": "Multi-Token Prediction",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mtp/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 11.1,
      "profile": {
        "Scientific": 3.5
      },
      "url": "https://artificialanalysis.ai/models/glm-4-5-air"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-glm-4-5-air",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/glm-4-5-air/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/glm-4-5-air.md"
}