Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things

2 months ago by cm0002 to c/Aii

Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …
unglueclass23 2 points 2 months ago

Waiting for some Cortecs provider to make it available.... I use these small models usually without thinking. Don't feel like thinking helps a lot; if you need thinking maybe just use a slightly more powerful model IMO.

path: 0 25343510, hotness: undefined, score: 2, children: 0
Aii
Aii

@programming.dev

login for more options
391
476
276

AI related news and articles.

Rules:

  • No Videos.
  • No self promotion: Don't post links to your articles.

go to feed...