Honestly to be expected with a 4b model. 12b/14b+ is the minimum in my experienc... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jeffhuys 5 months ago \| parent \| context \| favorite \| on: Ollama's new app Honestly to be expected with a 4b model. 12b/14b+ is the minimum in my experience to get decent results, unless you have a specific use-case for the 4b ones and fine-tune it to your use.

jay_kyburz 5 months ago [–]

Yeah, I tried Deepseek 8b as well and it was hopeless, but it was interesting to watch it think. I haven't seen that before.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact