+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Security, Privacy & Safety (https://www.datasculpting.ai/inference/forumdisplay.php?fid=23)
+--- Forum: Sandboxing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=78)
+--- Thread: containment for model-driven automation for Gemma (/showthread.php?tid=1209)
containment for model-driven automation for Gemma - kernelmike - 10-14-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of Ollama and 7900 XTX felt surprisingly usable once I tuned around tool calling.
If someone wants the exact settings I can clean them up and post them.
Re: containment for model-driven automation for Gemma - routeline23 - 10-15-2026
I don't think that's the whole story. I get why that seems right, but on mini PC the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: containment for model-driven automation for Gemma - vectorcrate98 - 10-16-2026
Tried to reproduce it just now. On dual 3090 with SGLang, I saw basically the same behavior.
Re: containment for model-driven automation for Gemma - emberrunner - 10-16-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: containment for model-driven automation for Gemma - mangovault67 - 10-16-2026
Good point. That matches what I saw on 4090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: containment for model-driven automation for Gemma - phasescope - 10-17-2026
That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me.