Posts: 35
Threads: 2
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 speculative decoding.
Curious whether that lines up with what other people are seeing.
This is mostly for local work rather than public serving.
trying not to rebuild again
Posts: 32
Threads: 5
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
measure twice, benchmark three times
Posts: 121
Threads: 15
Joined: Sep 2026
Reputation:
0
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.
image models by night, local pipelines by day
Posts: 51
Threads: 6
Joined: Aug 2026
Reputation:
0
I don't think that's the whole story. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps. At this point the real bottleneck is my patience.
serving stack tinkerer
Posts: 85
Threads: 12
Joined: Aug 2026
Reputation:
0
I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
LoRA tinkerer • dataset janitor
Posts: 63
Threads: 7
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. That matches what I saw on 5090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
