llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard
Published 2 months ago • verified publisher icon ggml-org

quantum K cache Q4_1 Q4_0 garbled output with Qwen-72b-Chat-iq3xxs / iq2xxs

Open DesperateZero opened this issue 1 year ago • 0 comments

q8_0 is ok.

DesperateZero avatar Mar 20 '24 03:03 DesperateZero