DEV Community

Discussion on: Running Local LLMs, CPU vs. GPU - a Quick Speed Test

Collapse
 
orlando_arroyo_1 profile image
Orlando Arroyo

Just a quick update: using a RTX 4070 Super gets 58.2tok/s

Collapse
 
maximsaplin profile image
Maxim Saplin

Is that a desktop card?

Collapse
 
oleksandr_davyskyba_5a399 profile image
Oleksandr Davyskyba

And RTX 4070 TI Super get 62tok/s