+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Apps / Utilities / Tools (https://www.datasculpting.ai/inference/forumdisplay.php?fid=18)
+--- Forum: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=20)
+--- Thread: CLI helpers for local models for Gemma (/showthread.php?tid=924)
Pages:
1
2
Re: CLI helpers for local models for Gemma - kernelmike - 10-12-2026
Quote:What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the p
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: CLI helpers for local models for Gemma - vramstream - 10-13-2026
same here on my side.
Re: CLI helpers for local models for Gemma - visionyard23 - 10-13-2026
Quote:same here on my side.
My first guess would be this: 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.