logoalt Hacker News

verdverm • yesterday at 4:58 PM • 2 replies • view on HN

You won't need a frontier size model for most tasks before long. Qwen 3.6 (small) punches way above its weight. I run it at home @8bit on an OEM Spark

Replies

kappar • yesterday at 5:22 PM

Second this, I am also running qwen 3.6 35b Q8 on a 5090 liquid getting around 250 tokens / second and it is plenty capable. I actually haven't even looked at models recently because I am happy with what I have.

And.. now I feel the need to look again. Darn, there goes my afternoon

dualvariable • yesterday at 5:08 PM

And corporations could run DeepSeek models on cloud hardware.

➕ show 1 reply