Hacker News new | ask | show | jobs
by bigyabai 61 days ago
A sparser model like Qwen3.6 35B A3B is probably your best choice: https://qwen.ai/blog?id=qwen3.6-35b-a3b
1 comments
hnfong 60 days ago
The 35B MOE will run faster, but 48GB RAM is more than enough to run the 27B dense model as well. It's just that token/s will be on the lower side.
link