{
  "slug": "glm-4-7-355b",
  "order": 31,
  "name": "GLM-4.7 (355B)",
  "baseTitle": "GLM-4.7 355B",
  "company": "Z.ai",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2025-12-22",
  "decoderType": "Sparse MoE",
  "attention": "GQA with QK-Norm",
  "layerMix": "92 GQA",
  "scale": "355B total, 32B active (9% active)",
  "totalParams": 355000000000,
  "activeParams": 32000000000,
  "context": "202,752",
  "contextTokens": 202752,
  "license": "MIT License",
  "kvCacheText": "368 KiB",
  "kvCacheKiB": 368,
  "kvCacheLevel": "Very high",
  "summary": "Immediate GLM predecessor that stays closer to the older GLM-4.5 style before the MLA shift.",
  "keyDetail": "Serves as the pre-MLA, pre-sparse-attention baseline and uses an MTP-3-style setup.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/glm-4-7-355b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/glm-4-7-355b.webp",
    "alt": "Figure 57: GLM-4.7 355B",
    "width": 960,
    "height": 931
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A721-glm-5",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison#%C2%A721-glm-5",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/zai-org/GLM-4.7/blob/main/config.json",
      "title": "zai-org/GLM-4.7"
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2508.06471",
      "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/"
    },
    {
      "slug": "mla",
      "label": "MLA",
      "name": "Multi-Head Latent Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mla/"
    },
    {
      "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": 17.4,
      "profile": {
        "Scientific": 3.2
      },
      "url": "https://artificialanalysis.ai/models/glm-4-7-non-reasoning"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-glm-4-7-355b",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/glm-4-7-355b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/glm-4-7-355b.md"
}