Hacker News new | ask | show | jobs
by vessenes 127 days ago
Confused as to why you wouldn’t integrate a local vlm if you want a local llm as the backbone. Plenty of 8b - 30b vlms out there that are visually competent.
1 comments

Its meant to be super light weight for people who run 1B, 3B, 8B or 20B models on skinny devices, one Pip install with high impact for one install :D