News for hackers. Stuff that matters.
Re:Qwen 3.6 27B is the sweet spot for local development by spike021 on Monday June 29, 2026 @01:44PM (#48722467)
Certainly won't work on my M4 Pro with 24GB lol
Re:Qwen 3.6 27B is the sweet spot for local development by MatthiasPortzel on Monday June 29, 2026 @02:18PM (#48723034)
I’m using it on a 48GB machine and it causes some lag, so it might be worse on 24, but it should run.

Unsloth recommends 18GB of RAM for Qwen3.6-27B (for their version of the model).

https://unsloth.ai/docs/models/qwen3.6

Re:Qwen 3.6 27B is the sweet spot for local development by whynotmaybe on Monday June 29, 2026 @01:54PM (#48722642)
I feel you!

Sent from my 8gb M2 Mac mini.

Re:Qwen 3.6 27B is the sweet spot for local development by kevinrineer on Monday June 29, 2026 @10:35PM (#48727929)
I'm still rocking my nvidia 2060, which I had purchased for $400 at the time.

I struggle to imagine purchasing multiple 1k+ cards on my own dime.