+- 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: anyone testing this? (/showthread.php?tid=323)
Ollama for power users: anyone testing this? - vectorember - 09-17-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between llama.cpp and vLLM for Gemma. The interesting difference for me has been prefill/decode split.
Interested in tradeoffs more than fan loyalty.
Re: Ollama for power users: anyone testing this? - tensorfield88 - 09-17-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: Ollama for power users: anyone testing this? - pixelspark - 09-18-2026
What worked for me was pretty simple. If you're on LM Studio, 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.
Re: Ollama for power users: anyone testing this? - vectorhouse71 - 09-18-2026
Quote:What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. A
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Ollama for power users: anyone testing this? - dockridge - 09-18-2026
worth checking the driver first.
Re: Ollama for power users: anyone testing this? - batchscope72 - 09-18-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: Ollama for power users: anyone testing this? - orbitbench6 - 09-21-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: Ollama for power users: anyone testing this? - edgeriver - 09-21-2026
same here on my side.
Re: Ollama for power users: anyone testing this? - fusedhall - 09-22-2026
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. Worth testing the simpler explanation before adopting the more interesting one.