this post was submitted on 23 Jun 2026
50 points (87.9% liked)

Futurology

4299 readers
1 users here now

founded 2 years ago
MODERATORS
voidx@futurology.today
Lugh@futurology.today
Espiritdescali@futurology.today
AwesomeLowlander@futurology.today
50
This new Chinese AI Is outperforming ChatGPT — and its open-source & runs locally (www.tomsguide.com)
submitted 2 weeks ago by Lugh@futurology.today to c/futurology@futurology.today
16 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] fluffykittycat@slrpnk.net 3 points 1 week ago

Given how memory is the bottleneck especially at the very low end it makes me wonder if one bit quantization of an extremely large model would be a gigabyte per gigabyte of ram better