Llama

{
  "alternatives": [],
  "artifacts": [
    {
      "uninstall": [
        {
          "quit": "app.llama.Llama"
        }
      ]
    },
    {
      "app": [
        "Llama.app"
      ],
      "target": "/Applications/Llama.app"
    },
    {
      "zap": [
        {
          "trash": [
            "~/.llama-app",
            "~/.local/bin/llama",
            "~/Library/Application Support/Llama",
            "~/Library/Application Support/LlamaBarn",
            "~/Library/Caches/app.llama.Llama",
            "~/Library/Caches/app.llamabarn.LlamaBarn",
            "~/Library/Caches/SentryCrash/Llama",
            "~/Library/HTTPStorages/app.llama.Llama",
            "~/Library/HTTPStorages/app.llamabarn.LlamaBarn",
            "~/Library/HTTPStorages/app.llamabarn.LlamaBarn.binarycookies",
            "~/Library/Preferences/app.llama.Llama.plist",
            "~/Library/Preferences/app.llamabarn.LlamaBarn.plist",
            "~/Library/WebKit/app.llamabarn.LlamaBarn"
          ]
        }
      ]
    }
  ],
  "auto_updates": 1,
  "categories": [],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Menu bar app for running local LLMs",
  "disable_reason": null,
  "disabled": 0,
  "display_name": "Llama",
  "enrichment_fetched_at": "2026-06-20T22:45:53+00:00",
  "first_seen": "2026-06-20T00:47:34+00:00",
  "full_token": "llama-app",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-06-18T13:58:02Z",
  "github_readme_excerpt": "# Llama\n\nLlama is a macOS menu bar app for running local LLMs.\n\n[Watch a 2-minute intro](https://www.youtube.com/watch?v=7AieF7rZUTc) \ud83d\udcfd\ufe0f\n\n\u003cbr\u003e\n\n![Llama](https://github.com/user-attachments/assets/df78f9ee-bb1d-4883-bf08-44371b0cd58a)\n\n\u003cbr\u003e\n\n## Install\n\n```sh\nbrew install --cask llama-app\n```\n\nOr download from [Releases](https://github.com/ggml-org/Llama-macOS/releases).\n\n## How it works\n\nLlama runs a local server at `http://localhost:8080/v1`.\n\n- **Install models** \u2014 from the built-in catalog\n- **Connect any app** \u2014 chat UIs, editors, CLI tools, scripts\n- **Models load when requested** \u2014 and unload when idle\n\n## Features\n\n- **100% local** \u2014 Models run on your device; no data leaves your Mac\n- **Small footprint** \u2014 `4 MB` native macOS app\n- **Zero configuration** \u2014 models are auto-configured with optimal settings for your Mac\n- **Recommended for your Mac** \u2014 suggests models sized to fit your hardware; browse the full catalog at [llama.app](https://llama.app)\n- **Standard storage** \u2014 models live in the Hugging Face cache (`~/.cache/huggingface/hub`), shared with `llama.cpp` and other HF-aware tools\n- **Built on llama.cpp** \u2014 from the GGML org, developed alongside llama.cpp\n\n## Works with\n\nLlama works with any OpenAI-compatible client.\n\n- **Chat UIs** \u2014 Chatbox, Open WebUI, BoltAI ([instructions](https://github.com/ggml-org/Llama-macOS/discussions/40))\n- **Editors** \u2014 VS Code, Zed, Xcode ([instructions](https://github.com/ggml-org/Llama-macOS/discussions/43))\n- **Editor extensions** \u2014 Cline, Continue\n- **CLI tools** \u2014 OpenCode ([instructions](https://github.com/ggml-org/Llama-macOS/discussions/44)), Claude Code ([instructions](https://github.com/ggml-org/Llama-macOS/discussions/45))\n- **Custom scripts** \u2014 curl, AI SDK, etc.\n\nYou can also use the built-in WebUI at http://localhost:2276 while Llama is running.\n\n## API examples\n\n```sh\n# list installed models\ncurl http://localhost:2276/v1/models\n```\n\n```sh\n# chat with Gemma 3 4B (assuming it\u0027s installed)\ncurl http://localh",
  "github_repo": "ggml-org/Llama-macOS",
  "github_stars": 1334,
  "github_topics": [
    "ai",
    "llama-cpp",
    "llms",
    "macos",
    "swift"
  ],
  "homepage": "https://github.com/ggml-org/Llama-macOS",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 29,
  "installs_365d": 29,
  "installs_90d": 29,
  "last_seen": "2026-06-20T00:47:34+00:00",
  "llm_generated_at": null,
  "llm_model": null,
  "names": [
    "Llama"
  ],
  "one_liner": null,
  "rank_30d": 2610,
  "rank_365d": 7456,
  "rank_90d": 4220,
  "raw_hash": "55c945f8874dd5a8",
  "ruby_source_path": "Casks/l/llama-app.rb",
  "tap": "homebrew/cask",
  "token": "llama-app",
  "version": "0.32.0",
  "why_use_this": null
}