Ollama

license

MIT

source

public

core features withheld

no

Ollama is MIT-licensed with the whole engine -- platform installers, an official Docker image, the local REST API, and the model library -- available at no cost and with no enterprise-only build. Ollama also sells hosted cloud inference alongside the engine, but that is a separate service rather than a capability withheld from the open core.

• https://api.github.com/repos/ollama/ollama recorded 2026-08-13

  Repository metadata - full_name ollama/ollama, language Go, license spdx_id MIT, public and not archived, 178,451 stars, 17,389 forks, last push 2026-08-12

• https://ollama.com/ recorded 2026-09-29

  The vendor home page states "Local models are always free." and separately sells cloud usage, so hosted inference is a paid service alongside the local engine.

• https://ollama.com/pricing recorded 2026-09-29

  The pricing page lists a Free plan at "$0" with "Run models locally" and a Download button, with paid plans described as "Use any cloud model with pay-as-you-go usage credits." for cloud models.

• https://raw.githubusercontent.com/ollama/ollama/main/LICENSE recorded 2026-09-29

  The repository LICENSE is the "MIT License" with "Copyright (c) Ollama" and the grant "to use, copy, modify, merge, publish, distribute, sublicense, and/or sell" copies, with no added restriction.

• https://raw.githubusercontent.com/ollama/ollama/main/README.md recorded 2026-09-29

  The README lists free install paths for macOS, Windows and Linux (for example "curl -fsSL https://ollama.com/install.sh | sh"), links "[Building from source](https://github.com/ollama/ollama/blob/main/docs/development.md)" in the public ollama/ollama repository, and states "The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub."; searched the body for enterprise, license key, licence, paid, pricing and commercial: none.

Adoption is measured from cumulative model-pull volume across Ollama's model library, corroborated by GitHub stars on the engine repository. The PyPI package named ollama is a client for talking to a local server, not the product's primary distribution channel, so its own download count is not used and there is no other package to measure adoption from.

• https://api.github.com/repos/ollama/ollama recorded 2026-08-13

  Repository metadata - 178,451 stars, 17,389 forks, language Go, last push 2026-08-12, not archived

• https://ollama.com/library recorded 2026-08-13

  Model library listing 233 models with an all-time cumulative pull count each - llama3.1 118.4M, deepseek-r1 91.3M, nomic-embed-text 82.2M, llama3.2 80M, and so on, summing to roughly 1.0 billion pulls. The counter is cumulative, not a rate; no monthly figure is published anywhere on the page.

• https://raw.githubusercontent.com/ollama/ollama/main/README.md recorded 2026-08-13

  Distribution channels confirmed - platform install scripts and manual installers for macOS, Windows and Linux plus the official ollama/ollama Docker Hub image. ollama-python and ollama-js are listed under Libraries, which is what the PyPI package is - a client for a local server, not the channel the product is obtained through.

Ollama runs models locally through a one-command CLI, an OpenAI-compatible REST API, and Python and JavaScript clients, with a model library spanning Llama, Qwen, Gemma, DeepSeek and gpt-oss and CLI launches for coding agents. No benchmark result is published for the runtime itself, so this reading comes from feature and model breadth rather than measured performance.

• https://docs.ollama.com/api/openai-compatibility recorded 2026-09-29

  The API docs page has an OpenAI compatibility section showing "Simple /v1/chat/completions example" against the local server at "localhost:11434/v1/chat/completions".

• https://ollama.com/library recorded 2026-09-29

  The library page, described as "Browse Ollama's library of models.", links 240 models including "/library/gpt-oss", "/library/gemma4" and "/library/deepseek-r1", with per-entry tag labels such as "thinking", "vision" and "embedding".

• https://raw.githubusercontent.com/ollama/ollama/main/README.md recorded 2026-09-29

  The README documents the REST API on "http://localhost:11434/api/chat", Python and JavaScript clients, and "ollama launch claude" plus integrations for Claude Code, Codex, Copilot CLI, DeepSeek Harness, Droid and OpenCode.