10-02-2026, 01:56 PM
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.
|
RTX 5090 local inference: what are you seeing?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
RTX 5090 local inference: what are you seeing? - by turbogrid11 - 10-02-2026, 09:39 AM
Re: RTX 5090 local inference: what are you seeing? - by amberhall - 10-02-2026, 01:56 PM
Re: RTX 5090 local inference: what are you seeing? - by sanevault - 10-02-2026, 03:02 PM
|