{
  "id": "llama-cpp",
  "name": "llama.cpp Server",
  "slogan": "The llama.cpp HTTP server: run quantized GGUF models on plain CPUs with an OpenAI-compatible API.",
  "category": "AI",
  "categorySlug": "ai",
  "tags": [
    "single-container"
  ],
  "license": {
    "spdx": "MIT",
    "class": "permissive"
  },
  "memoryMiB": 4096,
  "architectures": {
    "amd64": "published",
    "arm64": "published"
  },
  "trust": "listed",
  "verified": false,
  "status": "active",
  "installCommand": "levelrail-cli templates install llama-cpp --name my-llama-cpp",
  "deployFormats": [
    "cli",
    "api"
  ],
  "url": "https://levelrail.com/templates/llama-cpp/",
  "docsUrl": "https://github.com/ggml-org/llama.cpp/tree/master/tools/server",
  "sourceRepo": "https://github.com/ggml-org/llama.cpp",
  "markdownUrl": "https://levelrail.com/templates/llama-cpp.md",
  "jsonUrl": "https://levelrail.com/templates/llama-cpp.json",
  "indexable": true,
  "description": "The llama.cpp HTTP server: run quantized GGUF models on plain CPUs with an OpenAI-compatible API. Runs as a single container from the llama.cpp image, listening on port 8080; data is kept in named volumes.",
  "pinnedTag": "server",
  "licenseUrl": "https://github.com/ggml-org/llama.cpp/blob/master/LICENSE",
  "licenseClassLabel": "Permissive license",
  "needsConfig": false,
  "gpu": false,
  "firstRun": [],
  "services": [
    {
      "name": "llama-cpp",
      "image": "ghcr.io/ggml-org/llama.cpp",
      "tag": "server",
      "ports": [
        8080
      ],
      "volumes": [
        "llama_cpp_models -> /models"
      ]
    }
  ],
  "env": [
    {
      "service": "llama-cpp",
      "name": "LLAMA_CACHE",
      "kind": "preset"
    }
  ],
  "verifiedTag": null,
  "verifiedArches": [],
  "aliases": [],
  "findings": [],
  "compose": null,
  "deploy": {
    "cli": "levelrail-cli templates deploy llama-cpp --name my-llama-cpp",
    "api": "curl -X POST -H \"Authorization: Bearer $TOKEN\" \\\n  https://levelrail.example.com/api/v1/service-templates/llama-cpp/deploy",
    "stack": null,
    "terraform": null,
    "formats": [
      {
        "id": "cli",
        "label": "CLI",
        "lang": "bash",
        "code": "levelrail-cli templates deploy llama-cpp --name my-llama-cpp"
      },
      {
        "id": "api",
        "label": "API",
        "lang": "bash",
        "code": "curl -X POST -H \"Authorization: Bearer $TOKEN\" \\\n  https://levelrail.example.com/api/v1/service-templates/llama-cpp/deploy",
        "note": "Create a token in the dashboard first. This one-click route deploys it as a trial app you can keep or remove."
      }
    ]
  }
}
