alt Hacker NewsSame problem with every chinese model currently, they overthink way too much and take too much tokens and time.
Replies
EgregiousCube • last Sunday at 11:47 AM
A consequence of aggressive distillation?
szundi • last Sunday at 11:58 AM
[dead]
Same problem with every chinese model currently, they overthink way too much and take too much tokens and time.
A consequence of aggressive distillation?
[dead]
More or less, yeah. I've found mild success with deepseek-v4-flash though, and also Qwen3.5-122B-A10B-NVFP4 running locally, especially in terms of "doesn't overthink every single prompt" and somewhat reasonable quality. Really wishing for a 3.8 update of the 122B variant, that'd be really competitive (for local usage) :)