logoalt Hacker News

mft_last Sunday at 9:26 AM4 repliesview on HN

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.


Replies

embedding-shapelast Sunday at 9:49 AM

> the 122B version of 3.5

Yeah, this is what I'm holding out for, the NVFP4 variant of 3.5 122B is blazing fast with reasonable quality and even with max context fits perfectly within 96GB.

show 1 reply
pettijohnlast Sunday at 2:55 PM

SO MUCH THIS. I have Strix Halo with 128GB RAM and was a large and fast model like 122B A10B. Here's hoping!

cmrdporcupinelast Sunday at 4:04 PM

Absolutely. There's a glaring gap in the space for something about the size of Nemotron Super or just under, but actually ... competent.

The fantasy is a 100B or 80B model, but MoE and highly tuned for coding.

nsbklast Sunday at 9:46 AM

Indeed! That would be the sweet spot for my 2x3090 rig