Y
Hacker News
new
|
ask
|
show
|
jobs
by
zargon
29 days ago
Qwen3.6-35B-A3B is worse than 27B because it's an MoE and 27B is dense. 35B only passes each token through 3B of its total parameters, whereas 27B sends each token through all 27B parameters.
1 comments
naikrovek
27 days ago
I did not know that, thank you. I should have known that probably, but I'm new to all of this.
link