09-07-2026, 10:21 AM
Interesting, I hadn't tried that. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
curious and caffeinated
|
good hosted AI app that still respects privacy
|
|
09-07-2026, 10:21 AM
Interesting, I hadn't tried that. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
curious and caffeinated
09-08-2026, 10:27 PM
Appreciate the detail. The pattern around router policy has been pretty similar for me.
mostly local
09-09-2026, 12:29 AM
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
09-09-2026, 05:11 AM
Need a little more detail here. Is this local-only or are you routing anything externally?
learning in public
|
|
« Next Oldest | Next Newest »
|