LM Studio surprisingly handy: anyone testing this?

[fusedhall]

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 consumer GPUs.

I'm especially interested in mistakes worth avoiding.

I care more about stability than squeezing the last possible tokens/sec out of it.

[prompttinker44]

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

Interesting, I hadn't tried that. The pattern around reranking has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[vectorember]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.

[oxidemixer]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

[vectorcrate98]

Thanks, that helps. That matches what I saw on A6000.

[orbitbench6]

Appreciate the detail. 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.

[mellowwire98]

That matches what I was seeing. That matches what I saw on mini PC.

[vectorhouse71]

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality. At this point the real bottleneck is my patience.

[ggufwire22]

I think the bottleneck is somewhere else. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.