latest release actually worth attention with PyTorch

[amberrunner]

I'd start with the simpler stack.

Tried to reproduce it just now. On B200 with Ollama, I saw basically the same behavior. I expected the model choice to matter more than it did.

[modbench]

Not sure I agree there. I've seen people blame tokens/sec when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

I'm happy to test one more variant if you want a second data point.