best mini PC for local use with vLLM

[vramghost]

Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: LM Studio on A6000, keeping HBM constraints in mind from the start.

Feel free to tear it apart if you see something dumb.

[dockkite69]

same here on my side.

[promptfield]

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[rocmrunner40]

I hit almost the same issue last night.

[homelabhenry]

I hit almost the same issue last night.

that fixed it for me too.

[cobalttinker]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[promptfield]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. A lot of these threads en

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. Not glamorous advice, but repeatable baselines save a lot of time.

[cobalttinker]

Appreciate the detail. The pattern around HBM constraints has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[homelabhenry]

A couple things I'd check first. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time. At this point the real bottleneck is my patience.

[mangofield33]

Appreciate the detail. That matches what I saw on mini PC. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

I'm happy to test one more variant if you want a second data point.