logoalt Hacker News

avazhi • today at 2:42 AM • 2 replies • view on HN

I’m all for local models and getting away from Anthropic/OAI but Qwen 27B might as well be a horse drawn carriage compared to a 2026 Porsche. Like, I guess it’s useful if you had nothing better but acting like it’s comparable to anything the frontier models have is just disingenuous.


Replies

jeffyaw • today at 3:00 AM

disagree, it’s absolutely comparable. but an m5 max is where it shines. and there are 50 flags to finetune with llama server before you get it right. i do prefer llama server over mlx currently on mac as well.

➕ show 1 reply
metalspot • today at 11:23 AM

bro, you are looking at a repo that shows you exactly how to use it to achieve better results than a frontier model