Ollama

One command to download and run a language model on your own machine. The easiest honest answer to "how do I do this without a cloud".

At a glance

Where it runs
Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
Adult content
AllowedAdult content is permitted within the published rules.
Trains on your content
NoYour content is not used to train models.
Status
ActiveMaintained and working today.
Account needed
No
Licence
MIT
Cost
Free and open source.
What it keeps
Local. Conversations exist only in whatever client you point at it.

What it takes to run

Graphics memory
No GPU needed
System memory
8 GB, 16 GB recommended
Disk
about 20 GB
Runs on
Linux, macOS, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

ollama run llama3 downloads the weights, sets up the runtime and gives you a prompt. That is the entire onboarding, and it is why Ollama became the default recommendation for people who want a local model and not a hobby.

It exposes an HTTP API that a great many other tools — including several front-ends in this catalog — speak by default, so it is often the engine underneath something else.

It runs on CPU if you have no graphics card. It will be slow, and it will work.

Worth knowing before you start

What it does

Models it runs

How it relates to other tools

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered
Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub
181,082 17,892 forks.
Last commit
5 hours ago2026-09-16 00:37 UTC
Latest release
v0.34.1
Archived copy
Wayback Machine A snapshot, in case this one stops answering.

Categories

Something here wrong or out of date? Tell us — this page is only worth having if it is right.