Posts
12 posts · newest first
Technology
Does running a local LLM make sense for a small SaaS?
A framework for deciding whether a small SaaS should run a local language model, weighing cost, latency and privacy, with concrete defaults from the Ollama and llama.cpp documentation and no invented prices.
Blog
Why this site is built this way: simplicity, two languages, a corner of my own
Three choices behind this site: a simple structure with no maintenance burden, two-language content from the start, and a space that does not depend on someone else's platform. The choices and their costs.