Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by jeffhuys

3 days ago

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.

1 comment

jeffhuys

Reply

jay_kyburz  3 days 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.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities