Hacker News new | ask | show | jobs
by 3836293648 17 days ago
Yeah, I really should know. But I'm using whatever ollama gave me by default, which probably isn't optimal.
1 comments

Ollama uses 4 bit quants and a very short context window by default. It can easily break on anything more complex than a simple chat.
Oh, the context window I overrode immediately, the default one can't even reach my prompt in opencode, it's pushed out by all the pre- and post-amble. But I should probably try something less compressed next time I bother.