+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=51)
+---- Thread: setup notes worth sharing for Gemma (/showthread.php?tid=282)
Pages:
1
2
Re: setup notes worth sharing for Gemma - deltagrid - 09-20-2026
same here on my side.
Re: setup notes worth sharing for Gemma - mintstation99 - 09-20-2026
That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: setup notes worth sharing for Gemma - kernelgrid - 09-21-2026
I'd approach it in a boring order. On mini PC, 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.
Re: setup notes worth sharing for Gemma - relayforge - 09-21-2026
What worked for me was pretty simple. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: setup notes worth sharing for Gemma - audioriver - 09-21-2026
What worked for me was pretty simple. 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.