Olmo 3: Charting a path through the model flow to lead open-source AI

Olmo 3: Charting a path through the model flow to lead open-source AI (allenai.org)

mseri

376 points

Showing single thread. View full discussion?

embedding-shape

Well, GPUs are getting more VRAM, although it's pricey. But we didn't used to have 96GB VRAM GPUs at all, now they do exist :) But for the ones who can afford it, it is at least possible today. Slowly it increases.

refulgentis

a day ago

Agreed, in the limit, RAM go up. As billg knows, 128KB definitely wasn't enough for everyone :)

embedding-shape

a day ago

I'm already thinking 96GB might not be enough, and I've only had this GPU for 6 months or so :|

refulgentis

19 hours ago

Hehe me too…went all out on a MBP in 2022, did it again in April. Only upgrade I didn’t bother with was topping out at 128 GB of RAM instead of 64. Then, GPT-OSS 120B comes out and quickly makes me very sad I can’t use it locally