M3 Max for local use for DeepSeek

[torchshed]

Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.