Inference › Inference Engines › Other Engines v
tokens/sec tuning ideas

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
tokens/sec tuning ideas
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#5
09-06-2026, 06:29 PM
Thanks, that helps. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
tokens/sec tuning ideas - by orbitgarden - 09-04-2026, 11:26 PM
Re: tokens/sec tuning ideas - by byteyard - 09-05-2026, 01:27 AM
Re: tokens/sec tuning ideas - by promptfield - 09-05-2026, 01:56 AM
Re: tokens/sec tuning ideas - by vectorfield - 09-06-2026, 11:41 PM
Re: tokens/sec tuning ideas - by bytelab - 09-07-2026, 11:00 AM
Re: tokens/sec tuning ideas - by kernelghost - 09-06-2026, 02:08 PM
Re: tokens/sec tuning ideas - by vrambandit - 09-06-2026, 06:29 PM
Re: tokens/sec tuning ideas - by macrostack69 - 09-06-2026, 11:12 PM
Re: tokens/sec tuning ideas - by oxidegrove40 - 09-07-2026, 02:28 AM
Re: tokens/sec tuning ideas - by vrambandit - 09-07-2026, 06:57 AM
Re: tokens/sec tuning ideas - by kernelrunner - 09-07-2026, 12:00 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)