throughput per watt reality check: worth it?

[cacheplane98]

Did a bit of testing and thought I'd post the result here.

I tried this with Phi using MLX on A6000. The headline result was better than I expected, but NVFP4 still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.

[routecraft]

Interesting, I hadn't tried that. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.