Posts: 40
Threads: 3
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 prefill/decode split decides everything downstream.
Wondering if this is just where the whole space is heading now.
The part that surprised me was how much the boring details mattered more than the model choice.
Apple Silicon • MLX mostly
Posts: 49
Threads: 7
Joined: Oct 2026
Reputation:
0
I hit almost the same issue last night.
trying not to rebuild again
Posts: 73
Threads: 6
Joined: Sep 2026
Reputation:
0
My first guess would be this: 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: 58
Threads: 6
Joined: Sep 2026
Reputation:
0
I tested this tonight. On 7900 XTX with LM Studio, I saw basically the same behavior. I expected the model choice to matter more than it did.
Posts: 47
Threads: 4
Joined: Aug 2026
Reputation:
0
Appreciate the detail. 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.
learning in public
Posts: 44
Threads: 3
Joined: Oct 2026
Reputation:
0
That matches what I was seeing. That matches what I saw on GB200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Posts: 54
Threads: 7
Joined: Sep 2026
Reputation:
0
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Posts: 134
Threads: 18
Joined: Sep 2026
Reputation:
0
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.
watching release notes so you don't have to
