Ollama is the most widely used way to run open-weight language models on your own machine. One command downloads and runs models like Llama, Qwen, DeepSeek and their community variants, including fine-tunes that publishers describe as uncensored, with prompts processed locally rather than sent to a hosted service.
The project reports more than 9 million installs a month and over a billion model downloads, and states that prompts are never stored or trained on. The software itself is free; the real cost of self-hosting is your own hardware, and larger models need serious memory. A paid cloud tier handles models too big for a laptop.
