News for hackers. Stuff that matters.
Re:Qwen3.8 27B scores 52 on Artificial Analysis by ArvidSu on Monday August 17, 2026 @02:36PM (#49335643)
A ThinkingCap variant of Qwen 3.8 27b would be extremely interesting.

https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B

And then a Bonsai ternary on top of that model.

Re:Qwen3.8 27B scores 52 on Artificial Analysis by kees99 on Monday August 17, 2026 @03:04PM (#49336025)
Re: bonsai - unsloth's quants have Q2 (UD-IQ2) variants, which are more or less same in size.

...or did Prism do something special with their "bonsai" releases? I didn't notice anything like QAT being mentioned.

Re:Qwen3.8 27B scores 52 on Artificial Analysis by drob518 on Monday August 17, 2026 @03:12PM (#49336138)
There is some special sauce that they have. It’s not just a simple quant of another release. Or so they imply. I don’t have any insight into how it works or what the Bonsai special sauce is.
Re:Qwen3.8 27B scores 52 on Artificial Analysis by DoctorOetker on Wednesday August 19, 2026 @08:03PM (#49368816)
I suggest nobody repeats claims of "special sauce" if such "special sauce" is not understood.