logoalt Hacker News

WiSaGaNtoday at 4:15 PM1 replyview on HN

You probably meant Qwen3.8-35B-A3B. But judging from some of the words from their team, it seems unlikely unfortunately.


Replies

vorticalboxtoday at 5:10 PM

They normally release a 35b dense and an 27b moe (4B active per token)

For context 35B on my m4 runs at 10 tokens a second, 27B moe runs 50-60 tokens a second.