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 tgtweak on Wednesday April 22, 2026 @11:31PM (#47872002)
Depends entirely on quantization. Q6_K with max context length (262144) is ~40GB of VRAM.

Q8 with the same context wouldn't fit in 48GB of VRAM, it did with 128k of context.

[ Parent | on HN ]

There are no comments on this comment yet.