[SXX]

Now we need someone try run Kimi K2.6 on old Xeon and DDR3. After all these platforms do support up to 768GB RAM.

[Havoc]

It’ll work but yield a token per minute. With ancient servers the throughput is the limiting aspect not mem size

[segmondy]

You can run these on a turing machine. At what point is it not worth it? At some point the energy to generate each token matters. We often seen token per second. I think a missing metric is tokens per kilowatt. That is what really matters.

[SXX]

This is just like running Crysis via software rendering on CPU / llvmpipe. It dont have to be practical in order to be fun to try.