performance of quantized models

#6
by darvec - opened

Is there any comparison between the quantized version of kimi k2.5 and other good open-source models like Qwen3? For example, Qwen3-235B-A22B-Instruct-2507 is 470B large which is about the same size as UD-Q3_K_XL, but I am not sure if UD-Q3_K_XL has a better performance than qwen

Sign up or log in to comment