Ollama for power users

[fusedhall]

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

I'm comparing two approaches here: keep it simple on B200, 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?

This is mostly for local work rather than public serving.

[batchscope72]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.

[oxidemixer]

Thanks, that helps. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[pixelspark]

What exact setup are you running? Are you testing this on GB200 or something else?

[latentscope35]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

[orbitline]

subscribed, curious where this lands.

[prompttinker44]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[amberhall]

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

[edgeriver]

Tried to reproduce it just now. On A6000 with SGLang, I saw basically the same behavior. I expected the model choice to matter more than it did.

[pixelspark]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.