Join the community of Machine Learners and AI enthusiasts.
Sign Up
do you mean the Qwen2.5-Coder 32B? If so, we need to wait for Qwen3-Coder
https://x.com/huybery/status/1909669114341417344
+1
I've been using it just fine for the last couple days. It does take a while to think usually up to 60 seconds usually per prompt, but I usually ask deep questions so I don't really mind waiting.
How would I activate the previous version that way I can test between the two?
You meant the non-thinking mode? If so, add /no_think in your prompt
it's trained to think - probably with the idea to punctually use /no_think for some messages in a conversation where you don't want it to :) (The no think is probably more a product feature than something means to be used as default)
Noted. It thinks too long which is the problem. R1 and QwQ also took longer but are acceptable.
When I tested Qwen3, the difference of two modes is between an hour and a day (maybe longer)
It didn't wow me either, but... the thinking model is gonna not be as good if you disable the thinking, lol.
