{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-10-22T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/flock-this-that-model",
  "type": "tool",
  "slug": "flock-this-that-model",
  "canonical_url": "https://gtmstacker.com/registry/tool/flock-this-that-model/",
  "title": "FLock THIS/THAT Model — deterministic decision classifier",
  "description": "An MIT-licensed, self-hostable decision classifier from FLock.io and Oxford researchers that answers in a single forward pass with zero generated tokens, so unlike a text-generating LLM classifier it cannot parse-fail or drift; a 1.88B hybrid-attention model adapted from decider-2b, free to run locally.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "mcp-agents",
    "decision-models",
    "deterministic",
    "self-hostable"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "500c870adb30d67d446534d6314902b66e0561665f877a767a2ca1abfc323fa3",
  "date_published": "2026-10-15T00:00:00Z",
  "date_modified": "2026-10-15T00:00:00Z",
  "source": {
    "name": "github · FLock-io / this-that-model",
    "url": "https://github.com/FLock-io/this-that-model",
    "author": "flock_io"
  },
  "license": "MIT",
  "one_liner": "FLock's THIS/THAT Model is an MIT decision classifier that answers in one forward pass with zero generated tokens, so it cannot parse-fail.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_signal": "Free to self-host (MIT); also offered on the FLock API at $0 per million tokens (the model generates zero tokens by design, so there is nothing to meter).",
  "pricing_model": "free",
  "who_its_for": "A technical founder or lean GTM/RevOps team that needs a reliable yes/no or multiple-choice decision step (route, classify, gate) and wants a constrained, typed output that cannot hallucinate or fail to parse, running on weights they own.",
  "who_its_not_for": "Teams that need free-form text generation, or that prefer a fully managed hosted classifier with an SLA and no local inference to operate.",
  "aliases": [
    "this-that-model",
    "flock this that",
    "flock decision classifier",
    "this/that model"
  ],
  "alternatives": [
    "clef-cloudflare"
  ],
  "secondary_categories": [
    "mcp-agents"
  ],
  "last_verified": "2026-10-15",
  "evidence": {
    "claim_type": "mixed",
    "source_id": "https://github.com/FLock-io/this-that-model",
    "note": "SPDX MIT confirmed from the verbatim LICENSE file (copyright 2026 Cheng, Dai, Sun; Oxford and FLock.io); HF card corroborates 'mit; adapted from decider-2b under Apache-2.0' (both OSI-permissive). Self-hostable: pip install, BF16 safetensors on HF. Determinism verified structurally: one forward pass, no decoding loop, zero generated tokens, answer read from a hidden state against option-label tokens, cannot parse-fail. 39 stars, 9 commits. Authentic FLock-io org linked to the flock-io HF org."
  },
  "caveats": "It is NOT a 'Qwen3.5 base' model: it is a Qwen3.5-STYLE hybrid (18 of 24 layers DeltaNet linear attention, 6 full; 1.88B params) ADAPTED FROM decider-2b (Apache-2.0), not a Qwen3.5 fine-tune. The headline figures are vendor-claimed and unverified: ~31 ms latency on an RTX 5080 laptop GPU, 94.1% on a 68-question decision test said to beat GPT-5.6, Deepseek-4.1-flash, Kimi K3, and Jev; HF reports 1,640 downloads last month. Treat benchmark and latency as the maker's numbers.",
  "lead": "The **FLock THIS/THAT Model** is a decision classifier from FLock.io and researchers at the University of Oxford: given a question and a set of options, it returns one typed choice. Its distinguishing property is **determinism** — it runs a single forward pass with no decoding loop and generates **zero tokens**;…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 168,
      "text": "The **FLock THIS/THAT Model** is a decision classifier from FLock.io and researchers at the University of Oxford: given a question and a set of options, it returns one typed choice. Its distinguishing property is **determinism** — it runs a single forward pass with no decoding loop and generates **zero tokens**; the answer is read directly from a hidden state scored against the declared option-label tokens. Because the output is constrained to the declared labels, it cannot hallucinate a value or fail to parse, which is the usual failure mode when a text-generating LLM is pressed into service as a classifier. It is released under **MIT** and is free to self-host."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 527,
      "text": "against the declared option-label tokens. Because the output is constrained to the declared labels, it cannot hallucinate a value or fail to parse, which is the usual failure mode when a text-generating LLM is pressed into service as a classifier. It is released under **MIT** and is free to self-host.\n\n- SPDX **MIT** confirmed from the verbatim LICENSE file in the repo (copyright 2026 Zehua Cheng, Wei Dai, Jiahao Sun; University of Oxford and FLock.io). The Hugging Face model card corroborates \"License: mit\" and notes it is adapted from decider-2b, which is Apache-2.0 — both OSI-permissive, no license conflict.\n- Self-hostable: `pip install -e .` plus `python -m thisthat.server`; weights are BF16 safetensors on Hugging Face and run locally. Also offered on the FLock API at \"$0 per million tokens\" — accurate, since the model generates no tokens to meter.\n- Determinism verified structurally from the architecture description: one forward pass, no decoding loop, zero generated tokens, answer read from a hidden state against option-label tokens — the \"deterministic decision classifier\" framing holds.\n- **Correction to the surfacing label:** this is NOT a \"Qwen3.5 base\" model. It is a Qwen3.5-*style* hybrid-attention architecture (18 of 24 layers DeltaNet linear attention, 6 full attention; 1.88B params) adapted from decider-2b, not a Qwen3.5 base or fine-tune.\n- **Vendor-claimed, not independently tested:** ~31 ms latency on an RTX 5080 laptop GPU, and 94.1% on a 68-question decision test said to outperform GPT-5.6, Deepseek-4.1-flash, Kimi K3, and Jev; HF reports 1,640 downloads in the last month. These are the maker's figures.\n- Authentic `FLock-io` GitHub org (39 stars, 9 commits on a fresh 1.0 release), cross-linked to the official `flock-io` Hugging Face org; no name-squat. Surfaced via the 2026-10-15 X pull (poster flock_io); the post was used only as the surfacing signal, with verification grounded in the repo, LICENSE, and HF model card as untrusted content. Curated from the GTM Stacker signal registry (run 2026-10-15-registry-update-01); license verified 2026-10-15."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 356,
      "text": "official `flock-io` Hugging Face org; no name-squat. Surfaced via the 2026-10-15 X pull (poster flock_io); the post was used only as the surfacing signal, with verification grounded in the repo, LICENSE, and HF model card as untrusted content. Curated from the GTM Stacker signal registry (run 2026-10-15-registry-update-01); license verified 2026-10-15.\n\nDecision steps are everywhere in a GTM workflow — route this lead, classify this reply, gate this discount, pick a branch — and wiring them to a chat LLM means living with a model that can return the wrong shape, invent an option, or fail to parse, forcing retry-and-validate scaffolding around every call. A deterministic decision classifier removes that failure mode by construction: constrained to the declared labels, zero generated tokens, one pass. The honest read: the eye-catching numbers (31 ms, 94.1%, beating named frontier models and the proprietary Jev) are the maker's own benchmarks and are not independently verified, and the model is a hybrid architecture adapted from decider-2b rather than a plain Qwen3.5 fine-tune as first billed. What is verified is what matters most for adoption: the MIT license read from the LICENSE file, the zero-token deterministic design, and that it self-hosts for free. For a lean team that wants its decision logic owned, typed, and unable to drift, it is a license-clean option to evaluate alongside Cloudflare's Clef."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/flock-this-that-model/index.md",
    "html": "https://gtmstacker.com/registry/tool/flock-this-that-model/",
    "json": "https://gtmstacker.com/registry/tool/flock-this-that-model/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/flock-this-that-model/server.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "description": "The growth-systems practice of Theo Popov: AI-native enrichment, outbound, content engines and internal tooling for startups and venture programs. Its agent-native media property, the GTM Stacker Agent Registry, maintains a daily-updated catalog of open-source go-to-market and RevOps tools that both people and AI engines can discover, compare, and cite.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Growth Operations & GTM Systems",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "sameAs": [
          "https://www.linkedin.com/company/gtmstacker",
          "https://www.youtube.com/@gtmstacker",
          "https://www.instagram.com/gtmstacker/",
          "https://www.tiktok.com/@gtmstacker"
        ],
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "SoftwareApplication",
        "@id": "https://gtmstacker.com/registry/tool/flock-this-that-model/#software",
        "name": "FLock THIS/THAT Model — deterministic decision classifier",
        "identifier": "FLock-io/this-that-model",
        "description": "An MIT-licensed, self-hostable decision classifier from FLock.io and Oxford researchers that answers in a single forward pass with zero generated tokens, so unlike a text-generating LLM classifier it cannot parse-fail or drift; a 1.88B hybrid-attention model adapted from decider-2b, free to run locally.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/flock-this-that-model/",
        "datePublished": "2026-10-15T00:00:00Z",
        "dateModified": "2026-10-15T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "softwareHelp": "https://github.com/FLock-io/this-that-model",
        "license": "https://spdx.org/licenses/MIT.html",
        "codeRepository": "https://github.com/FLock-io/this-that-model",
        "keywords": "ai-infrastructure, mcp-agents, decision-models, deterministic, self-hostable",
        "author": {
          "@type": "Organization",
          "name": "FLock-io",
          "url": "https://github.com/FLock-io",
          "sameAs": [
            "https://github.com/FLock-io/this-that-model"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        },
        "isSimilarTo": [
          {
            "@type": "SoftwareApplication",
            "name": "Clef (Cloudflare) — open-weight decision model",
            "url": "https://gtmstacker.com/registry/tool/clef-cloudflare/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          }
        ]
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/flock-this-that-model/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "FLock THIS/THAT Model — deterministic decision classifier",
            "item": "https://gtmstacker.com/registry/tool/flock-this-that-model/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "FLock-io/this-that-model",
    "repository": {
      "url": "https://github.com/FLock-io/this-that-model",
      "source": "github"
    },
    "homepage": "https://github.com/FLock-io/this-that-model"
  }
}