benchmark result I don't trust: worth it?

[bytelab]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on M3 Max, or squeeze more out of the stack and deal with the complexity.

What would you pick if you had to live with it for a few months?

[orbitgarden]

Good point. The pattern around tool calling has been pretty similar for me. The logs were somehow calmer than I was.

[cudascope]

Good point. The pattern around tool calling has been pretty similar for me. The logs were somehow calmer than I was.

Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. I keep promising myself this is the last rebuild.

[batchpeak]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[mintstream9]

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.

[kernelghost]

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. N

that fixed it for me too.

[torchkite]

What worked for me was pretty simple. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

If you post your exact settings, people here can probably narrow it down pretty fast.