← Back to context Comment by theturtletalks 8 hours ago What kind of tps are you getting? 2 comments theturtletalks Reply kamranjon 8 hours ago Generally get 20-25tps - prefill is pretty good around 400-450tps. I have been using compaction at around 100k tokens but mostly just cause it was the default in pi coding agent - might see if i can expand it a bit. Lwerewolf 8 hours ago I've had it run to ~400k when debugging "obscure" (to it) sequences. Wouldn't recommend more.
kamranjon 8 hours ago Generally get 20-25tps - prefill is pretty good around 400-450tps. I have been using compaction at around 100k tokens but mostly just cause it was the default in pi coding agent - might see if i can expand it a bit. Lwerewolf 8 hours ago I've had it run to ~400k when debugging "obscure" (to it) sequences. Wouldn't recommend more.
Lwerewolf 8 hours ago I've had it run to ~400k when debugging "obscure" (to it) sequences. Wouldn't recommend more.
Generally get 20-25tps - prefill is pretty good around 400-450tps. I have been using compaction at around 100k tokens but mostly just cause it was the default in pi coding agent - might see if i can expand it a bit.
I've had it run to ~400k when debugging "obscure" (to it) sequences. Wouldn't recommend more.