Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
comparing models without fooling yourself for Phi
#1
Did a bit of testing and thought I'd post the result here.

I tried this with FLUX using MLX on A6000. The headline result was better than I expected, but tail latency still ended up being the limiting factor.

Curious if anyone else landed in the same place.
measure twice, benchmark three times
Reply


Messages In This Thread
comparing models without fooling yourself for Phi - by cacheline - 09-22-2026, 03:12 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)