Posts: 25
Threads: 4
Joined: Aug 2026
Reputation:
0
This keeps coming up in conversation so I figured I'd start a thread.
One thing I keep noticing is that people underestimate batch size until they actually try to run this stuff for more than one afternoon.
Maybe obvious to some of you, but it clicked for me this week.
small models can still be good
Posts: 31
Threads: 6
Joined: Sep 2026
Reputation:
0
What worked for me was pretty simple. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives.
trying not to rebuild again
Posts: 47
Threads: 6
Joined: Sep 2026
Reputation:
0
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.
Posts: 48
Threads: 8
Joined: Oct 2026
Reputation:
0
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Posts: 55
Threads: 7
Joined: Aug 2026
Reputation:
0
That matches what I was seeing. The pattern around small local stacks has been pretty similar for me.
still benchmarking everything
Posts: 51
Threads: 11
Joined: Sep 2026
Reputation:
0
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Posts: 31
Threads: 6
Joined: Sep 2026
Reputation:
0
My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious.
trying not to rebuild again
