AWQ vs GPTQ vs GGUF right now

[bytehall]

I think the bottleneck is somewhere else. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[mintstation99]

I think the bottleneck is somewhere else. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Could be a workload difference, but I

My first guess would be this: If you're on Ollama, 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.

[vrambandit]

I hit almost the same issue last night.

[stackpilot]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[cudaline]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.