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".
- Self-hosted
- Active
- Allowed adult content
- Open source
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
- Model library is curated Running an arbitrary Hugging Face model takes an extra step compared with the library.
- Less tunable than llama.cpp directly The simplicity comes from hiding the sampler and context settings some people want.
What it does
- One-command model download
- OpenAI-compatible API
- Runs on CPU
- Model library with quantisations
Models it runs
How it relates to other tools
- a frontend for llama.cpp — uses it as one of its engines
- an alternative to LM Studio
- has a frontend SillyTavern
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Something here wrong or out of date?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.