+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Security, Privacy & Safety (https://www.datasculpting.ai/inference/forumdisplay.php?fid=23)
+--- Forum: Local Privacy (https://www.datasculpting.ai/inference/forumdisplay.php?fid=76)
+--- Thread: privacy wins of local models for Gemma (/showthread.php?tid=1297)
privacy wins of local models for Gemma - rocmcrate26 - 10-15-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on Threadripper box, I ended up with decent performance, but the setup only really made sense once I adjusted around prefill/decode split.
Nothing scientific here, just practical notes from a real setup.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: privacy wins of local models for Gemma - mangoquill - 10-16-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, 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.