Kimi-K2-Thinking-UD-Q3_K_XL-00001-of-00010.gguf Generation - 5,231 tokens 604.63s 8.65 tokens/s
I currently have a 3970x with a bunch of 3090s.
Kimi-K2-Thinking-UD-Q3_K_XL-00001-of-00010.gguf Generation - 5,231 tokens 604.63s 8.65 tokens/s