{
  "slug": "kimi-k2-5",
  "order": 40,
  "name": "Kimi K2.5 (1T)",
  "baseTitle": "Kimi K2.5",
  "company": "Moonshot AI",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-01-27",
  "decoderType": "Sparse MoE",
  "attention": "MLA",
  "layerMix": "61 MLA",
  "scale": "1T total, 32B active (3.2% active)",
  "totalParams": 1000000000000,
  "activeParams": 32000000000,
  "context": "256,000",
  "contextTokens": 256000,
  "license": "Modified MIT License",
  "kvCacheText": "68.6 KiB",
  "kvCacheKiB": 68.6,
  "kvCacheLevel": "Low",
  "summary": "Native-multimodal Moonshot flagship that keeps the K2/DeepSeek-style MoE layout and pushes native context to 256k.",
  "keyDetail": "Keeps the 384-expert K2 backbone, but adds multimodal capabilities (not shown) and doubles the native context length.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/kimi-k2-5.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/kimi-k2-5.webp",
    "alt": "Figure 8: Kimi K2.5",
    "width": 960,
    "height": 930
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A72-moonshot-ais-kimi-k25-a-deepseek-like-model-at-a-1-trillion-parameter-scale",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A72-moonshot-ais-kimi-k25-a-deepseek-like-model-at-a-1-trillion-parameter-scale",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/config.json",
      "title": "moonshotai/Kimi-K2.5"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2602.02276",
      "title": null
    }
  ],
  "concepts": [
    {
      "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/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 19.4,
      "profile": {
        "Scientific": 6.9
      },
      "url": "https://artificialanalysis.ai/models/kimi-k2-5-non-reasoning"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-kimi-k2-5",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/kimi-k2-5/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/kimi-k2-5.md"
}