top | item 42867346

(no title)

monobot12 | 1 year ago

If you don't mind a speed of 1 token per second, you can run the largest R1 model on a 2021 iMac, as I just did.

discuss

order

btbuildem|1 year ago

Largest R1, as in the 671B? How do you accomplish that feat?

oynqr|1 year ago

Just do it? Llama.cpp doesn't load the entire thing into ram. It mmaps the file and the kernel takes care of the rest.

jeffbee|1 year ago

Are we speaking of a 2020-edition Intel 27" iMac or a 2021 M1?