desktop apps around local AI for Phi

[rocmcrate26]

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.

[mlxgarden]

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.

[rocmriley]

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.

[deltagrid]

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.