Please keep off topic stuff in the Off Topic forum

[torchtrack24]

Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not

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

[Data Sculpting]

That matches what I was seeing. That matches what I saw on 7900 XTX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[Data Sculpting]

subscribed, curious where this lands.