Posts: 20
Threads: 3
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.
Simple and boring is a valid answer.
Posts: 48
Threads: 5
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Posts: 28
Threads: 1
Joined: Sep 2026
Reputation:
0
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
mostly local
Posts: 41
Threads: 5
Joined: Aug 2026
Reputation:
0
My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Posts: 53
Threads: 7
Joined: Sep 2026
Reputation:
0
Thanks, that helps. The pattern around batch size has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Posts: 37
Threads: 4
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.
Posts: 37
Threads: 2
Joined: Sep 2026
Reputation:
0
My first guess would be this: 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.
mostly local
Posts: 36
Threads: 5
Joined: Sep 2026
Reputation:
0
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.