The easiest way for developers and tinkerers to run open models locally for free; cloud models cost extra.

Kenning's take

What it does

Ollama downloads and runs open models such as gpt-oss, Gemma and DeepSeek on a Mac, Windows or Linux computer, through a command line and a local API. It also offers cloud versions of larger models that run on Ollama's servers, paid for with usage credits. Ollama says prompts are not stored or used for training.

• Run open models locally on macOS, Windows and Linux
• Cloud models for larger open models
• Pay-as-you-go usage credits per million tokens
• Run several models at once on paid plans
• Open-source project on GitHub

Who it suits. Developers and technical users who want to run open models privately on their own hardware.

Key facts

Category

Developer tools

Made by

Ollama

How to get it

free download for macOS, Windows and Linux; cloud models need an account and credits

Works on

macOS, Windows, Linux, API

In the UK

Yes

Free plan

run models locally free, plus starter cloud usage credits

API price

cloud models priced per million tokens, e.g. gpt-oss:120b $0.15 input and $0.60 output

Pricing

Plan	Price	Billed
Pro	$20	month
Pro (annual)	$200	year
Max	$100	month
Team	$500	month
Enterprise	Custom pricing	custom

source

FAQ

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.