Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
RTX 5090 local inference: anyone testing this?
#3
Quote:Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow f

Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Reply


Messages In This Thread
Re: RTX 5090 local inference: anyone testing this? - by fastfield4 - 09-11-2026, 07:12 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)