Y
Hacker News
new
|
ask
|
show
|
jobs
by
pella
112 days ago
3bit hard-wired Llama 3.1 8B (
https://taalas.com/the-path-to-ubiquitous-ai/
)
1 comments
cyansmoker
112 days ago
3bit is a bit ridiculous. From that page I am unclear if the current model is 3 or 4bit. If it’s 4bit… well, NVIDIA showed that a well organized model can perform almost as well as 8bit.
link