+- 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
CLI helpers for local models for Gemma - modgarden - 10-08-2026
Has anyone else run into this?
I'm mostly working with DeepSeek in llama.cpp on M3 Max. The part I'm trying to understand is NVFP4.
Not looking for the perfect answer, mostly what worked in real use.
This is mostly for local work rather than public serving.
Re: CLI helpers for local models for Gemma - mlxgarden - 10-09-2026
that fixed it for me too. The logs were somehow calmer than I was.
Re: CLI helpers for local models for Gemma - rocmhouse90 - 10-10-2026
that fixed it for me too.
Re: CLI helpers for local models for Gemma - batchpeak - 10-10-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Re: CLI helpers for local models for Gemma - mlxgarden - 10-10-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4.
Re: CLI helpers for local models for Gemma - vectorport - 10-10-2026
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4.
I hit almost the same issue last night.
Re: CLI helpers for local models for Gemma - vramarch - 10-11-2026
Good point. The pattern around INT4 has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: CLI helpers for local models for Gemma - mlxgarden - 10-11-2026
I think the bottleneck is somewhere else. I've seen people blame token cost when the real issue was much more mundane.
Re: CLI helpers for local models for Gemma - rocmriley - 10-11-2026
Quote:I think the bottleneck is somewhere else. I've seen people blame token cost when the real issue was much more mundane.
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: CLI helpers for local models for Gemma - audioriver - 10-11-2026
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 plain path works, then add the faster path back in piece by piece.