Bz1sen@lemmy.worldtoPrivacy@lemmy.ml•Running local LLMs for privacy as an alternative to ChatGPT, MS Copilot etc.?
1·
11 days agoHow fast are response times and how useful are the answers of these open source models that you can run on a low end GPU? I know this will be a “depends” answer, but maybe you can share more of your experience. I often use Claude sonnet newest model and for my use cases it is a real efficiency boost if used right. I once mid of last year tested briefly an open source model from meta and it just wasn’t it. Or do we rather have to conclude that we’ll have to wait for another year until smaller open source models are more proficient?
Can you give more detail? I was a lifetime windows user and recently switched. I’m running Linux mint and steam and every game I tried on it was working as expected (admittedly my samplesize is not that big but from what I remember hades 2, slay the spire, horizon zero dawn, doom, civ5, rimworld, pal world were tried. No difference to windows. Maybe not the newest aaa games…)