llama

I compiled https://github.com/nomic-ai/gpt4all yesterday on FreeBSD, it wasn't straightforward, as I'm sure is often the case with Qt applications not native to FreeBSD. But I'm not going to port it because it's just nasty. I don't even understand why there's no standalone app with simple but...

Hello, Previously I tried to use Ollama on FreeBSD with my Nvidia GPU and it did not work, it uses CPU only, on the host or in a jail. Recently I have been using llama.cpp (version 8182, 28 Feb 2026) in a jail with Nvidia GPU support without issue, I will dump some notes for experienced users...