Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

Re:Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model by synergy20 on Thursday April 23, 2026 @10:30AM (#47876200)

wish I had a rtx5090 instead of the rtx4090 so I can run this, need 32GB VRAM I assume, no I use Linux and I do not enjoy MacOS, I wish x86 family has something like M5 Pro though.

[ Parent | on HN ]

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 ]