new here, what's your stack with LM Studio

[batchscope72]

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.

[orbitline]

My first guess would be this: On 7900 XTX, 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.

[vramscope]

Need a little more detail here. What model, what runtime, and roughly what context size?

[ggufwire22]

subscribed, curious where this lands.

[tensorkite]

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

[quiettoken]

I think the bottleneck is somewhere else. 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.

[ggufwire22]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[rocmplane]

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.

[quiettoken]

Thanks, that helps. The pattern around MoE serving has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[mangotinker73]

A couple things I'd check first. On B200, 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. I keep promising myself this is the last rebuild.