+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Agents (https://www.datasculpting.ai/inference/forumdisplay.php?fid=44)
+--- Thread: distillation that keeps useful behavior (/showthread.php?tid=421)
distillation that keeps useful behavior - sanevault - 09-22-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around router policy.
Happy to post more details if anyone wants them.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: distillation that keeps useful behavior - fusedriver - 09-23-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
Re: distillation that keeps useful behavior - plainworks - 09-23-2026
Quote:Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
A couple things I'd check first. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.