Skip to content

Ollama – Run Open AI Models Locally on Mac, Windows and Linux

Run open large language models such as Llama, Mistral and DeepSeek locally on macOS, Linux and Windows, with a simple command line and local API.

Freemium Free Plan Available Open Source Verified: November 2, 2026

Overview & In-Depth Description

Official Website & Direct Access

Visit the verified official product portal for Ollama.


Visit Ollama Website

Overview of Ollama

Ollama runs open AI models on your own computer or on its cloud. You start a model from the command line, for example ollama run gemma4, and it also serves a local REST API with Python and JavaScript libraries.

The GitHub README lists installers for macOS, Windows, Linux and Docker, and the project is MIT licensed. It supports model families such as Qwen, DeepSeek, Gemma and gpt-oss, and can launch coding agents like Claude Code and Codex through ollama launch.

Ollama's pricing page adds optional paid plans for cloud models billed per token with monthly usage credits. Developers who want local model serving or private experimentation are the main audience.

Key Features & Capabilities

  • Run models locally or in the cloud: Tagline: Run AI models locally and in the cloud (source: homepage)
  • REST API and client libraries: REST API on port 11434 with Python and JavaScript libraries (source: GitHub README)
  • Coding agent launching: ollama launch starts agents such as Claude Code, Codex, Copilot CLI and OpenCode (source: GitHub README)
  • OpenAI and Anthropic client compatibility: Works with compatible OpenAI and Anthropic clients (source: docs.ollama.com)
  • Zero data retention: Homepage says prompts are never stored or trained on (source: homepage)

Pricing & Plans

Plan Monthly Annual Limits / Credits Key Differences
Pay as you go $0 Not listed 3 concurrent requests Pay per token for cloud models; run models locally
Pro $20/mo $200/yr 3 concurrent requests; $60 usage credits/mo Larger Pro models
Max $100/mo Not listed 10 concurrent requests; $300 usage credits/mo Early access to newest models
Team (early access) $500/mo Not listed 10 concurrent requests; $1,000 shared usage credits/mo Unlimited users, centralized billing, priority support
Enterprise Custom Custom Not verified Model access controls, cost budgets, custom security questionnaires
  • Free plan: Available
  • Free trial: Not verified
  • Pricing model: Freemium
  • Pricing last checked: November 2, 2026

Official Ollama – Run Open AI Models Locally on Mac, Windows and Linux pricing page →

Strengths & Limitations of Ollama – Run Open AI Models Locally on Mac, Windows and Linux

Strengths

  • MIT-licensed project
  • Pay-as-you-go plan has no subscription
  • Runs on macOS, Windows, Linux and Docker

Limitations

  • Cloud usage is metered by credits and tokens
  • Concurrent request limits apply on paid plans
  • Pro fast mode listed as coming soon

Who Should Use This Tool?

  • Developers: local REST API and Python/JS libraries
  • Teams: shared usage credits and centralized billing on Team

Use Cases

  • Running open models such as Gemma, Qwen or DeepSeek from the command line
  • Serving a local REST API for an app
  • Using cloud-hosted models billed per token without a local GPU

How to Use Ollama – Run Open AI Models Locally on Mac, Windows and Linux

  1. Download Ollama for macOS, Windows or Linux
  2. Run a model, for example ollama run gemma4
  3. Call the local REST API or use the Python/JavaScript library

Privacy & Safety

  • Homepage states prompts are never stored or trained on and highlights zero data retention (https://ollama.com); full policy not reviewed

Information Not Verified

  • Hardware requirements: not verified
  • Free trial: not verified
  • Full privacy policy: not reviewed

Frequently Asked Questions About Ollama – Run Open AI Models Locally on Mac, Windows and Linux

Is Ollama free?

Yes, the Pay as you go plan is $0, with cloud models billed per token

Is Ollama open source?

The GitHub repository is MIT licensed

Does Ollama have an API?

Yes, a REST API on port 11434 plus Python and JavaScript libraries

What platforms does Ollama run on?

macOS, Windows, Linux and Docker per the GitHub README

How much is Ollama Pro?

$20/mo or $200/yr

Alternatives to Ollama – Run Open AI Models Locally on Mac, Windows and Linux

Other verified tools within the same category to consider alongside Ollama – Run Open AI Models Locally on Mac, Windows and Linux.

View all Code Assistants tools →