+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Apps / Utilities / Tools (https://www.datasculpting.ai/inference/forumdisplay.php?fid=18)
+--- Forum: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=20)
+--- Thread: desktop apps around local AI for Phi (/showthread.php?tid=847)
Pages:
1
2
Re: desktop apps around local AI for Phi - rocmcrate26 - 10-13-2026
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: desktop apps around local AI for Phi - mlxgarden - 10-15-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: desktop apps around local AI for Phi - rocmriley - 10-15-2026
My first guess would be this: If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: desktop apps around local AI for Phi - deltagrid - 10-15-2026
Maybe, but I had the opposite result. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.