new here, what's your stack on 5090

[rocmrunner40]

Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around MLX and GB200.

Simple and boring is a valid answer.

[thetagrid15]

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

[torchshed66]

Thanks, that helps. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.