{
  "slug": "ollama",
  "name": "Ollama",
  "category": "Runtimes / Inference",
  "tagline": "The one-command local model runner with a REST API on port 11434.",
  "kit_says": "If someone asks me how to get a model running in five minutes, I point here. It's the default backend half the directory plugs into.",
  "homepage": "https://ollama.com/",
  "repo": "https://github.com/ollama/ollama",
  "docs": "https://docs.ollama.com/",
  "license": "MIT",
  "platforms": [
    "macos-apple-silicon",
    "linux",
    "windows"
  ],
  "mac_studio_fit": "Primary",
  "what_it_is": "A local model runner and server. Pull models by name, chat in the terminal, and call a local REST API. Official Python (ollama-python) and JS (ollama-js) libraries.",
  "gap_role": "The easiest on-ramp: model management plus a stable local API that harnesses, UIs and memory layers already support.",
  "prerequisites": [
    "macOS, Linux or Windows"
  ],
  "install": {
    "macos-apple-silicon": [
      {
        "run": "curl -fsSL https://ollama.com/install.sh | sh",
        "note": "official script (README lists it for macOS)"
      },
      {
        "run": "# alternatives: brew install ollama   |   brew install --cask ollama-app   |   download https://ollama.com/download/Ollama.dmg"
      }
    ],
    "linux": [
      {
        "run": "curl -fsSL https://ollama.com/install.sh | sh"
      }
    ],
    "windows": [
      {
        "run": "irm https://ollama.com/install.ps1 | iex",
        "note": "PowerShell"
      }
    ]
  },
  "configure": [
    {
      "run": "ollama pull gemma4",
      "note": "example model name used in the README; pick any model from ollama.com/library"
    },
    {
      "run": "ollama run gemma4",
      "note": "interactive chat"
    }
  ],
  "verify": [
    {
      "run": "ollama --version",
      "expect": "prints a version string"
    },
    {
      "run": "curl -s http://localhost:11434/api/tags",
      "expect": "JSON list of locally pulled models"
    },
    {
      "run": "curl -s http://localhost:11434/api/chat -d '{\"model\":\"gemma4\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}],\"stream\":false}'",
      "expect": "JSON with message.content"
    }
  ],
  "rollback": [
    {
      "run": "ollama rm gemma4",
      "note": "remove a model"
    },
    {
      "run": "brew uninstall ollama   # or: brew uninstall --cask ollama-app",
      "note": "if installed via Homebrew"
    },
    {
      "run": "rm -rf ~/.ollama",
      "note": "deletes all downloaded models and keys; irreversible"
    }
  ],
  "caveats": [
    "Model names change frequently; confirm on ollama.com/library."
  ],
  "works_with": [
    "open-webui",
    "litellm",
    "aider",
    "mem0"
  ],
  "sources": [
    "https://github.com/ollama/ollama",
    "https://formulae.brew.sh/formula/ollama",
    "https://formulae.brew.sh/cask/ollama-app"
  ],
  "sponsored": false,
  "verified_on": "2026-10-15",
  "gap_score": {
    "value": null,
    "status": "pending test on Mac Studio",
    "baseline": "frontier reference (see /about#gap-score)"
  },
  "benchmarks": {
    "status": "pending test on Mac Studio",
    "rig": "Mac Studio, Apple Silicon, 128GB unified memory",
    "results": []
  },
  "hardware_tested": [],
  "repo_meta": {
    "stars": 183257,
    "stars_as_of": "2026-10-15",
    "last_push": "2026-10-15",
    "archived": false,
    "license_spdx": "MIT"
  },
  "stack_layer": "runtime",
  "summary": {
    "what": "One command to download and run a model.",
    "why": "The fastest way from zero to a local model."
  }
}