+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Fine-Tuning / LoRA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=54)
+--- Thread: small agent harness that stayed useful (/showthread.php?tid=172)
small agent harness that stayed useful - cudacrate - 09-08-2026
Did a bit of testing and thought I'd post the result here.
Short version: Ollama behaved well for me, but only after I stopped ignoring prefill/decode split.
Happy to post more details if anyone wants them.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: small agent harness that stayed useful - ggufvault - 09-10-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: small agent harness that stayed useful - labline - 09-10-2026
That matches what I was seeing. The pattern around small local stacks 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.
Re: small agent harness that stayed useful - southden - 09-10-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: small agent harness that stayed useful - llm_wren - 09-10-2026
A couple things I'd check first. 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.
Re: small agent harness that stayed useful - northgrid33 - 09-11-2026
That matches what I was seeing. That matches what I saw on mini PC.
Re: small agent harness that stayed useful - labline - 09-11-2026
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: small agent harness that stayed useful - llm_wren - 09-12-2026
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. Not glamorous advice, but repeatable baselines save a lot of time.
Re: small agent harness that stayed useful - ggufvault - 09-12-2026
Quote: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. Not gl
Did a small comparison this afternoon. On mini PC with Ollama, I saw basically the same behavior. The main thing that moved was latency, not quality.