Why I Run My Models Locally

Thu, 24 Sep 2026 00:00:00 +0000

Every prompt you send to a hosted LLM leaves your network. That includes the text you type, the files you attach, and whatever context your tools decide to pack around it. For a quick question about a regex that doesn’t matter. For your mailbox, your customers’ tickets or your company wiki, it matters a lot.

That is the main reason I run most of my models on my own hardware with Ollama. This post covers why, and where these models are useful in a self-hosted setup.

Ollama on M1CH's Log

Why I Run My Models Locally