Ollama · Independent

Ollama

The free engine that runs open models on your computer. A free app for macOS, Windows and Linux that downloads and runs open models on your own computer. It is the engine most local agents and coding tools connect to, through a local server at localhost:11434.

✓ Last verified October 15, 2026 from official sources

Pricing

Free for local models. Optional cloud plans: $20/mo (or $200/yr) and $100/mo, for Ollama-hosted models.

Best for

Powering VS Code, Continue, OpenClaw and Hermes with local models. The engine behind Open WebUI.

Privacy · Skill

Local. Ollama states it does not see prompts or data when you run locally. Cloud models are optional and can be disabled with OLLAMA_NO_CLOUD=1. Skill level: Beginner.

What it's great at

Connecting agents and coding tools to local models
Fast setup: one command per model

What it can do

One command downloads and runs a model, e.g. "ollama run gemma4:e2b"
Always-on local API at http://localhost:11434, with OpenAI-compatible (/v1) and Anthropic-compatible endpoints
Built-in integrations: "ollama launch" sets up OpenClaw, Hermes, Claude Code, Codex and others
"ollama ps" shows whether a model fits fully on the GPU

Example tasks to try

"ollama run gemma4:e4b" to chat privately on a 16GB laptop

Start in 5 minutes

Download from ollama.com/download and install
Open Terminal or PowerShell and run "ollama run gemma4:e2b" (8GB) or "gemma4:e4b" (16GB)
Point your agent at http://localhost:11434

Go to Ollama's official page →

Watch out for

Default context is 4,096 tokens; raise it to 64K+ for agents.

Compare it

LM Studio vs Ollama vs Open WebUI: running local models

Similar agents

Anthropic

Automation you can self-host, with AI agent steps.

Official sources

Prices change often. Confirm on the vendor's page before you buy. We're independent, and no vendor pays for placement.