Posts: 41
Threads: 7
Joined: Sep 2026
Reputation:
0
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 reranking.
I'm especially interested in mistakes worth avoiding.
I care more about stability than squeezing the last possible tokens/sec out of it.
I expected the biggest difference to come from the model, but the stack around it mattered at least as much.
small models can still be good
Posts: 51
Threads: 4
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Posts: 41
Threads: 7
Joined: Sep 2026
Reputation:
0
What exact setup are you running? What model, what runtime, and roughly what context size?
small models can still be good
Posts: 37
Threads: 3
Joined: Sep 2026
Reputation:
0
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
I'm happy to test one more variant if you want a second data point.
Posts: 45
Threads: 2
Joined: Aug 2026
Reputation:
0
Interesting, I hadn't tried that. That matches what I saw on GB200.
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Mostly CUDA, sometimes wrong, usually measured
Posts: 53
Threads: 7
Joined: Sep 2026
Reputation:
0
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
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.
Mostly CUDA, sometimes wrong, usually measured
