Hacker News new | ask | show | jobs
by kgeist 16 days ago
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.
1 comments

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.