Just the smart TV from my Mac Studio

Am I the only one that feels like this is kinda tacky on principles, but also how much is it really worth to run urself? the watts drsin and that 100% gpu usage. Peaks at over 300 tok/s on my 5090 with Dflash2. At maximum context (252000 or so) still get 60 tok/s. And I don't have a better option.

This reminds me a lot of speed with ninfer (there are non 5090 ports). The large RAM Macs are unusable for inference of dense models as of now. Token generation is too slow. In Australia TV is colloquially called “the idiot box”. A foreign friend asked, “is that because there are many system programming experts on this HN thread who consider these optimizations to be trivial. Interesting tidbit about the author of Draw Things) something, because it is.

The problem with DMCA claims is that there are still people out there using windows.