Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
benchmark result I don't trust: anyone testing this?
#8
What exact setup are you running? What model, what runtime, and roughly what context size?
measure twice, benchmark three times
Reply


Messages In This Thread
Re: benchmark result I don't trust: anyone testing this? - by cacheline - 10-19-2026, 12:36 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)