{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-10-03T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/strata",
  "type": "tool",
  "slug": "strata",
  "canonical_url": "https://gtmstacker.com/registry/tool/strata/",
  "title": "Strata",
  "description": "Strata is an open-source local inference engine that runs large open models (the maker demos a 125B-parameter model) on a single consumer GPU, exposing an OpenAI/Anthropic-compatible API on localhost. Open source: yes (MIT); self-hostable. Free OSS; ~8.2k stars; active (~628 commits). Needs an NVIDIA or AMD GPU with 12 GB or more.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "mcp-agents",
    "inference",
    "local-models",
    "self-hostable",
    "openai-compatible"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "b684bc0666213df53c0ccc5272b4525f1247d6b9eb014a916caac2dc1fc640e8",
  "date_published": "2026-10-03T00:00:00Z",
  "date_modified": "2026-10-03T00:00:00Z",
  "source": {
    "name": "Niko1221 · GitHub",
    "url": "https://github.com/Niko1221/Strata"
  },
  "license": "MIT",
  "one_liner": "Strata is an open-source inference engine that runs large open models on one consumer GPU, with an OpenAI and Anthropic-compatible API on localhost.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_model": "free",
  "who_its_for": "A team that wants to run large open models locally on a single consumer GPU and call them through an OpenAI or Anthropic-compatible API on localhost, so existing agents and tooling point at their own box instead of a hosted provider.",
  "who_its_not_for": "A team with no suitable GPU (it needs an NVIDIA or AMD card with 12 GB or more), or one that wants a mature, battle-tested runtime rather than an early v0.1.x project, or that would rather call a managed API than operate inference itself.",
  "aliases": [
    "strata",
    "Niko1221/Strata",
    "Strata"
  ],
  "alternatives": [
    "magnitude",
    "atlas-localai",
    "atlas-ollama"
  ],
  "secondary_categories": [
    "mcp-agents"
  ],
  "last_verified": "2026-10-03",
  "evidence": {
    "claim_type": "vendor-claim",
    "source_id": "https://github.com/Niko1221/Strata",
    "note": "MIT per repo (license read from GitHub metadata, not guessed); ~8,158 stars; ~628 commits; active (pushed 2026-10-03) (github.com/Niko1221/Strata, verified 2026-10-03). README: 'Run a 125-billion-parameter AI model on your own gaming PC' on an NVIDIA/AMD card with 12 GB+ (Windows/Linux); one-click install; OpenAI/Anthropic-compatible API on localhost. The 125B demo uses heavy quantisation (IQ3_S, 128K ctx) and is the maker's own, not benchmarked here."
  },
  "caveats": "Verified from the primary repo (2026-10-03); no independent testing here. Early project (v0.1.x) despite high star velocity, so expect rough edges and churn. The headline '125B model on a gaming PC' relies on aggressive quantisation (IQ3_S), which trades quality for fit, so test output quality for your task before relying on it. Requires an NVIDIA or AMD GPU with 12 GB or more. Surfaced via X.",
  "lead": "Strata is an open-source local inference engine: it runs large open models on a single consumer GPU and exposes an OpenAI and Anthropic-compatible API on localhost, so agents and tools you already have can point at your own machine instead of a hosted provider. Open source: yes (MIT); self-hostable; free…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 118,
      "text": "Strata is an open-source local inference engine: it runs large open models on a single consumer GPU and exposes an OpenAI and Anthropic-compatible API on localhost, so agents and tools you already have can point at your own machine instead of a hosted provider. Open source: yes (MIT); self-hostable; free OSS. It has ~8.2k stars, ~628 commits, and the maker demonstrates a 125-billion-parameter model running on a gaming PC with an NVIDIA or AMD card of 12 GB or more."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "What it does"
      ],
      "est_tokens": 234,
      "text": "you already have can point at your own machine instead of a hosted provider. Open source: yes (MIT); self-hostable; free OSS. It has ~8.2k stars, ~628 commits, and the maker demonstrates a 125-billion-parameter model running on a gaming PC with an NVIDIA or AMD card of 12 GB or more.\n\nStrata is about running big models on hardware you own. The pitch is a one-click install for Windows or Linux that stands up an inference engine on your GPU and serves it through an OpenAI/Anthropic-compatible endpoint on localhost, with optional image input. Because the API mirrors the hosted providers, you can repoint an existing agent at it without rewriting the integration. The demonstration that draws attention is a 125-billion-parameter model on a single gaming PC, achieved with heavy quantisation (the README shows IQ3_S at 128K context). Open source: yes (MIT); self-hostable; free OSS. It needs an NVIDIA or AMD GPU with 12 GB or more."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 242,
      "text": "at it without rewriting the integration. The demonstration that draws attention is a 125-billion-parameter model on a single gaming PC, achieved with heavy quantisation (the README shows IQ3_S at 128K context). Open source: yes (MIT); self-hostable; free OSS. It needs an NVIDIA or AMD GPU with 12 GB or more.\n\n- MIT per repo (license read from GitHub metadata, not guessed); ~8,158 stars; ~628 commits; active (pushed 2026-10-03) (github.com/Niko1221/Strata, verified 2026-10-03).\n- README: \"Run a 125-billion-parameter AI model on your own gaming PC\"; NVIDIA or AMD card with 12 GB or more; Windows or Linux; one-click install; OpenAI/Anthropic-compatible API on localhost; optional image input.\n- Surfaced in the GTM Stacker X/Twitter signal report (2026-10-03 pass); license/facts independently verified 2026-10-03.\n- The 125B-on-a-consumer-GPU demo uses aggressive quantisation (IQ3_S) and is the maker's own (vendor-claim); not independently benchmarked here."
    },
    {
      "index": 3,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 294,
      "text": "with 12 GB or more; Windows or Linux; one-click install; OpenAI/Anthropic-compatible API on localhost; optional image input. - Surfaced in the GTM Stacker X/Twitter signal report (2026-10-03 pass); license/facts independently verified 2026-10-03. - The 125B-on-a-consumer-GPU demo uses aggressive quantisation (IQ3_S) and is the maker's own (vendor-claim); not independently benchmarked here.\n\nRunning your own models is where agent economics stop being a hosted-API line item, and the barrier has always been hardware. Strata's bet is that heavy quantisation plus a one-click install lets a single consumer GPU serve a model large enough to be useful, behind the same OpenAI/Anthropic API your agents already speak. For a GTM team that wants prospecting, enrichment, or support agents running on owned infrastructure with no per-token bill, that is worth a trial on a spare box. The honest read: the headline number leans on IQ3_S quantisation, which costs output quality, and it is an early v0.1.x project, so benchmark the quality on your own tasks and treat the \"125B on a gaming PC\" line as a demo, not a guarantee. You also need a 12 GB-plus NVIDIA or AMD card to start."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/strata/index.md",
    "html": "https://gtmstacker.com/registry/tool/strata/",
    "json": "https://gtmstacker.com/registry/tool/strata/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/strata/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/strata/#software",
        "name": "Strata",
        "identifier": "Niko1221/Strata",
        "description": "Strata is an open-source local inference engine that runs large open models (the maker demos a 125B-parameter model) on a single consumer GPU, exposing an OpenAI/Anthropic-compatible API on localhost. Open source: yes (MIT); self-hostable. Free OSS; ~8.2k stars; active (~628 commits). Needs an NVIDIA or AMD GPU with 12 GB or more.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/strata/",
        "datePublished": "2026-10-03T00:00:00Z",
        "dateModified": "2026-10-03T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/MIT.html",
        "codeRepository": "https://github.com/Niko1221/Strata",
        "keywords": "ai-infrastructure, mcp-agents, inference, local-models, self-hostable, openai-compatible",
        "author": {
          "@type": "Organization",
          "name": "Niko1221",
          "url": "https://github.com/Niko1221",
          "sameAs": [
            "https://github.com/Niko1221/Strata"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        },
        "isSimilarTo": [
          {
            "@type": "SoftwareApplication",
            "name": "Magnitude",
            "url": "https://gtmstacker.com/registry/tool/magnitude/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          }
        ]
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/strata/#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": "Strata",
            "item": "https://gtmstacker.com/registry/tool/strata/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "Niko1221/Strata",
    "repository": {
      "url": "https://github.com/Niko1221/Strata",
      "source": "github"
    }
  }
}