Tommaso GagliardoniFeb 26

Going into the rabbithole of testing local LLMs right now. I don't have a dedicated GPU, but 32 GiB of RAM should be enough for anyone.

#ai #huggingface #selfhost #localai #ollama #heretic #qwen #mistral

Show threadTommaso Gagliardoni
Interesting, it seems that Qwen 2.5 Coder is actually less aggressive than Qwen 3.5 in rejecting sensitive topics.
Feb 26 at 11:01amWeb