You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Right now, decode rates on using llama.cpp and termux on my phone are pretty bad when using GPU (for the Llama 3.2 3B model). Any suggestions on how to get it up? Looking for around 20 to 25 tokens/sec.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Right now, decode rates on using llama.cpp and termux on my phone are pretty bad when using GPU (for the Llama 3.2 3B model). Any suggestions on how to get it up? Looking for around 20 to 25 tokens/sec.
Beta Was this translation helpful? Give feedback.
All reactions