quiet dual-GPU build advice

[batchwire]

Did a bit of testing and thought I'd post the result here.

Short version: PyTorch behaved well for me, but only after I stopped ignoring MoE serving.

Happy to post more details if anyone wants them.

[tensorport]

I hit almost the same issue last night.

[bytegarden73]

I hit almost the same issue last night.

Interesting, I hadn't tried that. 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.

[latentpeak22]

Maybe, but I had the opposite result. I've seen people blame quant drift when the real issue was much more mundane.

[thetatinker77]

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.

[llm_wren]

Not sure I agree there. I've seen people blame small local stacks when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[tensorworks]

Tried to reproduce it just now. On GB200 with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it did.

[sanevault]

What worked for me was pretty simple. If you're on LM Studio, 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.