RTX 5090 local inference: what are you seeing?

[turbogrid11]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on mini PC, or squeeze more out of the stack and deal with the complexity.

What would you pick if you had to live with it for a few months?

[amberhall]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.

[sanevault]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.