alt Hacker NewsBring it on! Hoping that they release smaller sizes of Qwen3.8. I use the 35B MoE and 27B dense models locally and most of the time I don’t need to reach out to Claude. Extremely useful specially when requests include sensitive and/or personal data
Replies
zer0gravity • yesterday at 10:49 AM
This seems more of a battle for frontier AI supremacy. I'm afraid that small capable models have been left in the dust. Big labs don't really want to hand over the golden eggs goose to the end user. Possibly the hardware vendors(e.g. Nvidia) may want to play in that area as well, to pull money from all parties.
➕ show 4 replies
worldsavior • yesterday at 9:55 AM
That's a 2.4T model, how would they reduce this to 35B and still give some accuracy? That's a completely different arch.
➕ show 1 reply
nsagent • yesterday at 3:48 PM
[flagged]
I think everyone is hoping this!
It would be great if they'd release an MoE model somewhere between the 35B size of 3.6 and the 122B version of 3.5 - it could be a great balance of speed and ability for people with reasonably powerful but not insane home computers.