+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Ollama / LM Studio / Desktop Runtimes (https://www.datasculpting.ai/inference/forumdisplay.php?fid=38)
+--- Thread: Ollama for power users (/showthread.php?tid=415)
Pages:
1
2
Ollama for power users - fusedhall - 09-23-2026
Did a bit of testing and thought I'd post the result here.
Short version: llama.cpp behaved well for me, but only after I stopped ignoring router policy.
Curious if anyone else landed in the same place.
Re: Ollama for power users - vectorember - 09-23-2026
Quote:Did a bit of testing and thought I'd post the result here.
A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: Ollama for power users - visionyard23 - 09-23-2026
Thanks, that helps. The pattern around embeddings has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Ollama for power users - edgeriver - 09-24-2026
Not sure I agree there. I've seen people blame prefill/decode split when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Ollama for power users - fusedhall - 09-24-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt? Turns out 'just one more test' was a lie.
Re: Ollama for power users - vectorhouse71 - 09-24-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.
Re: Ollama for power users - vectorember - 09-25-2026
Thanks, that helps. I ended up in about the same place using LM Studio.
Re: Ollama for power users - vectorcrate98 - 09-25-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
Re: Ollama for power users - quietstack - 09-28-2026
Appreciate the detail. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Ollama for power users - audionode8 - 09-29-2026
I hit almost the same issue last night.