Posts: 27
Threads: 2
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
team red, team patient
Posts: 52
Threads: 9
Joined: Oct 2026
Reputation:
0
A couple questions before I guess too hard. Are you testing this on B200 or something else?
Posts: 76
Threads: 8
Joined: Aug 2026
Reputation:
0
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
I'm happy to test one more variant if you want a second data point.
learning in public
Posts: 19
Threads: 0
Joined: Sep 2026
Reputation:
0
Thanks, that helps. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.