MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second 1 month ago
Nice benchmark, thanks! Which quants did you choose for the self hosted models?
HN user
Nice benchmark, thanks! Which quants did you choose for the self hosted models?
People say you will have less problems with AMD but I am using a Nvidia GPU for years now (on Cachyos and Pop OS) without issues. I'm using Steam and Proton pretty much exclusively though.
DP over USB-C is coming soon: https://www.youtube.com/watch?v=3OAiOfCcYFM&t=1681s