News for hackers. Stuff that matters.

A comment on Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model. Parent comment

Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model by fwipsy on Thursday April 23, 2026 @10:33AM (#47876237)
I was just wishing I had 24gb rather than 16gb so I could run q4 comfortably. Unsloth q4 variants are 15.4gb-17.6gb so it seems at least well worth trying on a 4090.
[ Parent | on HN ]

There are no comments on this comment yet.