Files
variet_llm/scripts/qwen_intermediate.csv

12 lines
881 B
CSV

model,label,avg,best,mode,vram,t,ub,b,kv,split,mmap
UD-IQ4_NL,pure-GPU minbatch,65.11,65.49,GPU,19177,t4,ub64,b256,q4_0/q4_0,,
UD-IQ4_NL,pure-GPU nommap small,65.01,65.36,GPU,19672,t4,ub128,b512,q4_0/q4_0,,nommap
UD-IQ4_NL,pure-GPU row-split,13.65,14.82,GPU,19427,t4,ub128,b512,q4_0/q4_0,row,
UD-IQ4_NL,pure-GPU ts=0.5,0.5,64.92,65.23,GPU,19664,t4,ub128,b512,q4_0/q4_0,,
UD-IQ4_NL,pure-GPU all-tricks,64.72,64.89,GPU,19171,t4,ub64,b256,q4_0/q4_0,,nommap
UD-IQ4_NL,tune t=2,64.87,65.13,GPU,19170,t2,ub64,b256,q4_0/q4_0,,
UD-IQ4_NL,tune t=6,64.88,65.17,GPU,19168,t6,ub64,b256,q4_0/q4_0,,
UD-IQ4_NL,tune t=8,64.5,64.77,GPU,19168,t8,ub64,b256,q4_0/q4_0,,
UD-IQ4_NL,tune ub=256 b=1024,64.73,64.98,GPU,20640,t4,ub256,b1024,q4_0/q4_0,,
UD-IQ4_NL,tune ub=256 b=2048,63.69,64.94,GPU,20614,t4,ub256,b2048,q4_0/q4_0,,
UD-IQ4_NL,tune kv=q8_0/q8_0,64.78,65.08,GPU,20422,t4,ub64,b256,q8_0/q8_0,,