Posts: 26
Threads: 3
Joined: Aug 2026
Reputation:
0
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once workstation thermals becomes important.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving.
The part that surprised me was how much the boring details mattered more than the model choice.
Posts: 30
Threads: 6
Joined: Aug 2026
Reputation:
0
What worked for me was pretty simple. If you're on Ollama, 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.
Posts: 46
Threads: 7
Joined: Sep 2026
Reputation:
0
Need a little more detail here. Is this local-only or are you routing anything externally?
Posts: 28
Threads: 4
Joined: Sep 2026
Reputation:
0
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
curious and caffeinated
Posts: 54
Threads: 3
Joined: Sep 2026
Reputation:
0
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Posts: 39
Threads: 4
Joined: Sep 2026
Reputation:
0
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.
Posts: 31
Threads: 2
Joined: Oct 2026
Reputation:
0
Appreciate the detail. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Posts: 63
Threads: 1
Joined: Sep 2026
Reputation:
0
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
still benchmarking everything
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
What exact setup are you running? Are you testing this on mini PC or something else?
Mostly CUDA, sometimes wrong, usually measured
