Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
running local models on a phone
#11
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
curious and caffeinated
Reply
#12
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

If you post your exact settings, people here can probably narrow it down pretty fast.
Reply


Forum Jump:


Users browsing this thread: