CLI helpers for local models for Gemma

[modgarden]

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.

[mlxgarden]

that fixed it for me too. The logs were somehow calmer than I was.

[rocmhouse90]

that fixed it for me too.

[batchpeak]

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.

[mlxgarden]

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.

[vectorport]

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.

[vramarch]

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.

[mlxgarden]

I think the bottleneck is somewhere else. I've seen people blame token cost when the real issue was much more mundane.

[rocmriley]

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.

[audioriver]

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.