Posts: 33
Threads: 7
Joined: Sep 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 long context becomes important.
Interested in tradeoffs more than fan loyalty.
This is mostly for local work rather than public serving. Turns out 'just one more test' was a lie.
Posts: 66
Threads: 7
Joined: Sep 2026
Reputation:
0
A couple questions before I guess too hard. Are you testing this on B200 or something else?
Posts: 62
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: 341
Threads: 51
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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
measure twice, benchmark three times
Posts: 43
Threads: 5
Joined: Sep 2026
Reputation:
0
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Posts: 137
Threads: 16
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. 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.
throughput matters, but tail latency matters too
Posts: 62
Threads: 5
Joined: Sep 2026
Reputation:
0
Quote:Interesting, I hadn't tried that. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether
I'd approach it in a boring order. If you're on Ollama, 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
trying not to rebuild again
Posts: 41
Threads: 4
Joined: Aug 2026
Reputation:
0
That matches what I was seeing. The pattern around token cost has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Posts: 49
Threads: 5
Joined: Sep 2026
Reputation:
0
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
Quote:Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Mostly CUDA, sometimes wrong, usually measured
