{
  "slug": "step-3-5-flash-196b",
  "order": 41,
  "name": "Step 3.5 Flash (196B)",
  "baseTitle": "Step 3.5 Flash 196B",
  "company": "StepFun",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-02-01",
  "decoderType": "Sparse MoE",
  "attention": "GQA with 3:1 sliding-window attention",
  "layerMix": "36 sliding-window + 12 global",
  "scale": "196B total, 11B active (5.6% active)",
  "totalParams": 196000000000,
  "activeParams": 11000000000,
  "context": "262,144",
  "contextTokens": 262144,
  "license": "Apache License 2.0",
  "kvCacheText": "192 KiB",
  "kvCacheKiB": 192,
  "kvCacheLevel": "High",
  "summary": "Throughput-oriented MoE model that stays competitive with much larger DeepSeek-style systems.",
  "keyDetail": "Uses MTP-3 during both training and inference for unusually high throughput.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/step-3-5-flash-196b.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/step-3-5-flash-196b.webp",
    "alt": "Figure 12: Step 3.5 Flash 196B",
    "width": 960,
    "height": 940
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A73-stepfuns-step-35-flash-good-performance-at-great-tokens-sec-throughput",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight#%C2%A73-stepfuns-step-35-flash-good-performance-at-great-tokens-sec-throughput",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/stepfun-ai/Step-3.5-Flash/blob/main/config.json",
      "title": "stepfun-ai/Step-3.5-Flash"
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/pdf/2602.10604",
      "title": null
    }
  ],
  "concepts": [
    {
      "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/"
    },
    {
      "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,
      "profile": {
        "Scientific": 13.4
      },
      "url": "https://artificialanalysis.ai/models/step-3-5-flash"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-step-3-5-flash-196b",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/step-3-5-flash-196b/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/step-3-5-flash-196b.md"
}