🍺 BREW Explorer

← all formulae

ollama

brew install ollama v0.30.10 MIT

Command-line tool for running, creating, and sharing large language models locally using optimized inference.

Why you might care

Ollama lets you run open-source LLMs (Llama, Mistral, etc.) on your own machine without external APIs, keeping data private and avoiding cloud costs. It handles model download, quantization, and GPU acceleration automatically, and provides a simple REST API for integration into workflows or scripts. Useful for developers, researchers, and anyone who wants local, self-hosted AI without cloud dependencies.

Categories

Alternatives

LM Studio vLLM llama.cpp text-generation-webui
66.2k
30-day installs · #87
225.7k
90-day · #82
569.0k
365-day · #127

Runtime dependencies

Build dependencies

Links

Blurb generated by claude-haiku-4-5 on today.

Raw metadata
{
  "aliases": [],
  "alternatives": [
    "LM Studio",
    "vLLM",
    "llama.cpp",
    "text-generation-webui"
  ],
  "build_dependencies": [
    "cmake",
    "go"
  ],
  "categories": [
    "language-runtime",
    "ai",
    "ml",
    "library"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "mlx-c"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Create, run, and share large language models (LLMs)",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:38+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "ollama",
  "github_default_branch": null,
  "github_last_commit_at": null,
  "github_readme_excerpt": null,
  "github_repo": null,
  "github_stars": null,
  "github_topics": [],
  "homepage": "https://ollama.com/",
  "homepage_og_description": "Ollama is the easiest way to automate your work using open models, while keeping your data safe.",
  "homepage_og_image": "https://ollama.com/public/og.png",
  "homepage_title": "Ollama",
  "installs_30d": 66224,
  "installs_365d": 568989,
  "installs_90d": 225654,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": "2026-06-20T23:42:37+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "ollama",
  "oldnames": [],
  "one_liner": "Command-line tool for running, creating, and sharing large language models locally using optimized inference.",
  "optional_dependencies": [],
  "rank_30d": 87,
  "rank_365d": 127,
  "rank_90d": 82,
  "raw_hash": "0365d0b896053daa",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/o/ollama.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "0.30.10",
  "versioned_formulae": [],
  "why_use_this": "Ollama lets you run open-source LLMs (Llama, Mistral, etc.) on your own machine without external APIs, keeping data private and avoiding cloud costs. It handles model download, quantization, and GPU acceleration automatically, and provides a simple REST API for integration into workflows or scripts. Useful for developers, researchers, and anyone who wants local, self-hosted AI without cloud dependencies."
}