>>106956761
Why is my GLM4.6 retarded?

prompt eval time = 342.81 ms / 29 tokens ( 11.82 ms per token, 84.59 tokens per second)
eval time = 11465.64 ms / 336 tokens ( 34.12 ms per token, 29.30 tokens per second)
total time = 11808.45 ms / 365 tokens