Ollama
Ollama runs open models on your own computer. It’s MIT-licensed, installs on macOS, Windows and Linux, has an official Docker image, and puts every model you download behind the same local API.
What it does now
- One command to start.
ollama run gemma4:e2bdownloads the model and starts a chat in your terminal. - A local API for your apps. Ollama serves a REST API on
localhost:11434, has official Python (pip install ollama) and JavaScript (npm i ollama) libraries, and works with existing OpenAI and Anthropic clients. - Coding agents on open models.
ollama launch claude,ollama launch codexandollama launch opencodestart Claude Code, Codex CLI or OpenCode from your project directory, running on Ollama. - Cloud models when your hardware runs out. Sign in and add the
:cloudtag, as ingemma4:cloud, to run a model on Ollama’s servers. Ollama says it doesn’t use cloud prompts to train models, and you can turn cloud features off for local-only use. - A large model library, including Gemma, Qwen, DeepSeek, gpt-oss, Kimi, GLM and MiniMax, at ollama.com/search.
Plans (checked 1 Nov 2026 on ollama.com/pricing)
Running models on your own hardware is free and unlimited. The paid plans are for cloud models.
| Plan | Price | Highlights |
|---|---|---|
| Pay as you go | $0 | Local models; cloud models billed per token; 3 concurrent requests |
| Pro | $20/mo, or $200/yr | $60 of cloud usage credits a month, larger Pro models |
| Max | $100/mo | $300 of credits a month, early access to new models, 10 concurrent requests |
| Team (early access) | $500/mo | Unlimited users, $1,000 of shared credits a month, central billing, priority support |
| Enterprise | Custom | Model access controls, spending budgets per user and API key, dedicated support |
Who it’s for
- Developers who want a local model behind a simple API, without running an inference server by hand.
- Anyone curious about coding agents on open models, through
ollama launch. - Teams with privacy rules that require prompts to stay on their own hardware.
Alternatives
Prefer a desktop app with a model browser? Look at LM Studio. Want the engine itself? Try llama.cpp. We compare all three in Ollama vs LM Studio vs llama.cpp. For Jan, LocalAI, vLLM and more, see our 8 best Ollama alternatives.