Running a language model on your own machine has obvious appeal: your data stays local, there's no per-token bill and you can work offline. But the choice usually starts in the wrong place, with a parameter count or a leaderboard. A model that excels at code completion may be a poor choice for ...
Source: [Dev.to](https://dev.to/inferama/how-to-choose-a-local-llm-for-your-hardware-without-guessing-16jb)