>>106166819
>>106166833
no no im using chat completion, what gguf maker are you using? im using the unsloth quant
but i posted text completion thing because some things might get into the chat completion thing
heres the full chat completion screenshot
./llama-server --model ~/TND/AI/glmq3kxl/GLM-4.5-Air-UD-Q3_K_XL-00001-of-00002.gguf -ot ffn_up_shexp=CUDA0 -ot exps=CPU -ngl 100 -t 6 -c 16384 --no-mmap -fa
this is how i start it