Best workstation layout for local models

[kernelhouse70]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about MoE serving.

Would rather learn from your scars than collect my own all at once.

[edgequill]

My first guess would be this: If you're on Ollama, 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.

[signaltrack44]

A couple things I'd check first. On dual 3090, 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.

[sanevault]

A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once

Interesting, I hadn't tried that. The pattern around long context has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[nanobrook]

That matches what I was seeing. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[phasenode]

Thanks, that helps. The pattern around quant drift has been pretty similar for me.

[vramghost]

Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.

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

[fastbench]

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