Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like batch size decides everything downstream.
Curious whether that lines up with what other people are seeing.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
measure twice, benchmark three times
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
measure twice, benchmark three times
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
What exact setup are you running? Are you testing this on 4090 or something else?
measure twice, benchmark three times
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
Quote:What exact setup are you running? Are you testing this on 4090 or something else?
Interesting, I hadn't tried that. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
measure twice, benchmark three times
Posts: 23
Threads: 1
Joined: Sep 2026
Reputation:
0
I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
Quote:I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. Once yo
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. Once you know the plain path works, then add the faster path back in piece by piece.
measure twice, benchmark three times
Posts: 28
Threads: 4
Joined: Sep 2026
Reputation:
0
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. The pattern around speculative decoding has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
measure twice, benchmark three times
Posts: 47
Threads: 6
Joined: Sep 2026
Reputation:
0
Appreciate the detail. 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 felt usable.
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
measure twice, benchmark three times
