Hacker News new | ask | show | jobs
by mythz 462 days ago
Concur with Gemma2 being underwhelming, I dismissed it pretty quickly but gemma3:27b is looking pretty good atm.

BTW mistral-small:24b is also worth mentioning (IMO best local model) and phi4:14b is also pretty strong for its size.

mistral-small was my previous local goto model, testing now to see if gemma3 can replace it.

1 comments

One more vote for Mistral for local models. The 7B model is extremely fast and still good enough for many prompts.