Posts: 57
Threads: 9
Joined: Aug 2026
Reputation:
0
This keeps coming up in conversation so I figured I'd start a thread.
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with tokens/sec.
Maybe obvious to some of you, but it clicked for me this week.
Posts: 34
Threads: 3
Joined: Aug 2026
Reputation:
0
Appreciate the detail. That matches what I saw on M3 Max. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
I'm happy to test one more variant if you want a second data point.
Posts: 121
Threads: 15
Joined: Sep 2026
Reputation:
0
Good point. That matches what I saw on mini PC. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
image models by night, local pipelines by day
Posts: 48
Threads: 9
Joined: Sep 2026
Reputation:
0
that fixed it for me too.
Posts: 63
Threads: 7
Joined: Sep 2026
Reputation:
0
Ran a quick check on my box. On 7900 XTX with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.
Posts: 37
Threads: 4
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. I ended up in about the same place using MLX.
