non-AI thing you built recently on A6000

[thetapath]

I figured I'd ask here before changing everything.

I'm mostly working with Llama in Ollama on 4090. The part I'm trying to understand is workstation thermals.

If you've tested something similar, what did you keep and what did you stop bothering with?

[plainember52]

following this because I'm in the same boat.

[southpatch]

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. Not glamorous advice, but repeatable baselines save a lot of time.

[bytelab]

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. Not glamorous advi

A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[batchfield55]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[vectorcrate98]

Appreciate the detail. I ended up in about the same place using SGLang.

[pixelspark]

Good point. I ended up in about the same place using LM Studio. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[tensorriver]

I'd start with the simpler stack.