Posts: 25
Threads: 4
Joined: Aug 2026
Reputation:
0
Curious what people here are seeing.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling small local stacks.
Not looking for the perfect answer, mostly what worked in real use.
small models can still be good
Posts: 46
Threads: 7
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. The pattern around reranking 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: 35
Threads: 4
Joined: Oct 2026
Reputation:
0
Quote:That matches what I was seeing. The pattern around reranking has been pretty similar for me. I got better results once I stopped chasing one metric an
Interesting, I hadn't tried that. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
trying not to rebuild again
Posts: 112
Threads: 12
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
context windows are not a product strategy
Posts: 34
Threads: 3
Joined: Aug 2026
Reputation:
0
subscribed, curious where this lands.
Posts: 38
Threads: 6
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. The pattern around INT4 has been pretty similar for me.
retrieval before vibes
Posts: 59
Threads: 8
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Posts: 30
Threads: 4
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
learning in public
