News for hackers. Stuff that matters.

A comment on TurboQuant: Redefining AI efficiency with extreme compression.

Re:TurboQuant: Redefining AI efficiency with extreme compres... by ssijak on Wednesday March 25, 2026 @07:32AM (#47515947)
For my grug brain can somebody translate this to ELIgrug terms?

Does this mean I would be able to run 500b model on my 48gb macbook without loosing quality?

[ Parent | on HN ]
Re:TurboQuant: Redefining AI efficiency with extreme compres... by x_may on Wednesday March 25, 2026 @07:48AM (#47516067)
KV cache compression, so how much memory the model needs to use for extending its context. Does not affect the weight size.
[ Parent | on HN ]
Re:TurboQuant: Redefining AI efficiency with extreme compres... by prabal97 on Thursday March 26, 2026 @02:57PM (#47534274)
I wrote this more intuitive explanation. I think you might find it helpful!

https://prabal.ca/posts/google-long-context-cheaper/

[ Parent | on HN ]