Hacker News Reader

Hah, and now we can't summarize this thread any more because your comment will turn thinking off!

FWIW, their readme states /nothink - and that's what works for me.

>/think and /nothink instructions: Use those words in the system or user message to signify whether Qwen3 should think. In multi-turn conversations, the latest instruction is followed.

https://github.com/QwenLM/Qwen3/blob/main/README.md

Thanks, /nothink works!

So, Qwen3 1.7b is about the same speed just slightly worse than Gemma3 4b which is pretty impressive.

Qwen3 4b passes all 200 tests and is much faster than Mistral Small 3.1 24b or Gemma3 27b.

Thanks!

Turns out just is not the word here. My benchmark is made using conversations, where there is a SystemMessage and some structured content in a UserMessage.

But Qwen3 seems to ignore /no_think when appended to the SystemMessage. I can try to add it to the structured content but that will be a bit weird. Would have been better to have a "think" parameter like temperature.