Comment by xiphias2
9 months ago
Have you compared it with 8-bit QwQ-17B?
In my evals 8 bit quantized smaller Qwen models were better, but again evaluating is hard.
9 months ago
Have you compared it with 8-bit QwQ-17B?
In my evals 8 bit quantized smaller Qwen models were better, but again evaluating is hard.
There’s no QwQ 17B that I’m aware of. Do you have a HF link?
You're right, sorry...I just tested Qwen models, not QwQ, I see QwQ only has 32B.
No worries, QwQ is the thinking model from Qwen, it’s a common misconception.
I think they should’ve named it something else.