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
With the recent release of a series of 8x22B models, my dual 4090 setup is struggling to cope with the memory demands of the new generation of open-source models. For some models, excessive quantization could significantly impact their performance in executing agent tasks. Therefore, we hope users with hardware resources can share their findings here.
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
-
With the recent release of a series of 8x22B models, my dual 4090 setup is struggling to cope with the memory demands of the new generation of open-source models. For some models, excessive quantization could significantly impact their performance in executing agent tasks. Therefore, we hope users with hardware resources can share their findings here.
Beta Was this translation helpful? Give feedback.
All reactions