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
Hello everyone! I've run the Llama 3B Instruct model on mobile using termux and llama.cpp. However, the performance is quite poor, with a prefill time of around 4.5 seconds and a decode time of around 5 seconds. These become worse when 8B is used. Any suggestions to improve these metrics?
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
-
Hello everyone! I've run the Llama 3B Instruct model on mobile using termux and llama.cpp. However, the performance is quite poor, with a prefill time of around 4.5 seconds and a decode time of around 5 seconds. These become worse when 8B is used. Any suggestions to improve these metrics?
Beta Was this translation helpful? Give feedback.
All reactions