best mini PC for local use

[dockkite69]

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

This isn't revolutionary, but the combination of MLX and 4090 felt surprisingly usable once I tuned around tail latency.

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

[quantghost]

I'd start with the simpler stack.

[cobalttinker]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[mintstream9]

Need a little more detail here. Are you testing this on dual 3090 or something else?

[lablab]

I'd start with the simpler stack.

[mintquill]

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.

[oxiderunner]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

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

[cobalttinker]

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

[vramghost]

Appreciate the detail. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

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

[mintquill]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.