News for hackers. Stuff that matters.

A comment on Qwen 3.6 27B is the sweet spot for local development. Parent comment

Re:Qwen 3.6 27B is the sweet spot for local development by madduci on Monday June 29, 2026 @01:29PM (#48722254)
Like everybody got 128 GB RAM..
[ Parent | on HN ]
Re:Qwen 3.6 27B is the sweet spot for local development by sleepyeldrazi on Monday June 29, 2026 @01:39PM (#48722391)
I've been running it almost since launch on a 3090 (24gb vram), you really don't need that much. Second hand those are really cheap and i get 50-70 t/s (with MTP at 2), full ctx. IQ4_NL (unsloth) on this model seems suspiciously competent, and after the (by now not so recent) updates to q4 KV on llama.cpp, I just keep going back to it after dsv4pro disappointed me for the 100th time because it gave up on a task.
[ Parent | on HN ]
Re:Qwen 3.6 27B is the sweet spot for local development by dofm on Monday June 29, 2026 @01:31PM (#48722281)
Doesn't need it at Q4 at least; it'll run in 64GB.
[ Parent | on HN ]
Re:Qwen 3.6 27B is the sweet spot for local development by intothemild on Monday June 29, 2026 @03:23PM (#48723878)
Q6 can run with 256k at Q4 on 32gb easy.

200k @ K : Q5_0 V: 4_1 (which is a bit of a sweet spot)

[ Parent | on HN ]