{
  "slug": "tiny-aya-3-35b",
  "order": 44,
  "name": "Tiny Aya (3.35B)",
  "baseTitle": "Tiny Aya 3.35B",
  "company": "Cohere",
  "country": "Canada",
  "flag": "🇨🇦",
  "date": "2026-02-13",
  "decoderType": "Dense",
  "attention": "GQA with 3:1 sliding-window attention",
  "layerMix": "27 sliding-window + 9 global",
  "scale": "3.35B parameters",
  "totalParams": 3350000000,
  "activeParams": 3350000000,
  "context": "8,192",
  "contextTokens": 8192,
  "license": "Creative Commons Attribution-NonCommercial 4.0",
  "kvCacheText": "72 KiB",
  "kvCacheKiB": 72,
  "kvCacheLevel": "Low",
  "summary": "Compact multilingual model from Cohere with a rare parallel transformer block.",
  "keyDetail": "Runs attention and the MLP in parallel while mixing RoPE with NoPE.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/tiny-aya-3-35b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/tiny-aya-3-35b.webp",
    "alt": "Figure 35: Tiny Aya 3.35B",
    "width": 960,
    "height": 938
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A710-tiny-aya-a-335b-model-with-strong-multilingual-support",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A710-tiny-aya-a-335b-model-with-strong-multilingual-support",
      "title": null
    },
    {
      "label": "From scratch",
      "href": "https://github.com/rasbt/LLMs-from-scratch/tree/main/ch05/15_tiny-aya",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/CohereLabs/tiny-aya-base/blob/main/config.json",
      "title": "CohereLabs/tiny-aya-base"
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2603.11510",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "nope",
      "label": "NoPE",
      "name": "No Positional Embeddings",
      "url": "https://llm-atlas-7or.pages.dev/concepts/nope/"
    },
    {
      "slug": "gqa",
      "label": "GQA",
      "name": "Grouped-Query Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/gqa/"
    },
    {
      "slug": "swa",
      "label": "SWA",
      "name": "Sliding Window Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/swa/"
    }
  ],
  "aai": {
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 4.8,
      "profile": {
        "Scientific": 2.6
      },
      "url": "https://artificialanalysis.ai/models/tiny-aya-global"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-tiny-aya-3-35b",
  "family": "dense",
  "url": "https://llm-atlas-7or.pages.dev/models/tiny-aya-3-35b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/tiny-aya-3-35b.md"
}