best mini PC for local use on 7900 XTX

[byteyard]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with prefix caching.

Maybe obvious to some of you, but it clicked for me this week.

[thetatinker77]

This keeps coming up in conversation so I figured I'd start a thread.

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.

[homelabhenry]

subscribed, curious where this lands.

[batchfield55]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[promptfield]

Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[cobalttinker]

Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more opti

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. Worth testing the simpler explanation before adopting the more interesting one.

[batchfield55]

My first guess would be this: On mini PC, 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.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[homelabhenry]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

[dockkite69]

A couple things I'd check first. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[homelabhenry]

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?