ThomasBaruzier's picture
Upload perplexity.md
ae9fcd9 verified
Quant Size (MB) PPL Size (%) Accuracy (%) PPL error rate
IQ1_S 754 38.2733 12.80 25.21 0.68
IQ1_M 810 23.9542 13.75 40.28 0.41
IQ2_XXS 904 22.7872 15.34 42.34 0.41
IQ2_XS 983 14.4025 16.68 66.99 0.24
IQ2_S 1012 13.6118 17.17 70.88 0.22
IQ2_M 1087 12.6560 18.45 76.24 0.20
Q2_K_S 1142 12.4745 19.38 77.35 0.20
Q2_K 1215 11.5168 20.62 83.78 0.18
IQ3_XXS 1223 10.8327 20.76 89.07 0.17
IQ3_XS 1327 10.2693 22.52 93.96 0.16
Q3_K_S 1386 32.8121 23.52 29.41 0.62
IQ3_S 1389 10.2409 23.57 94.22 0.16
IQ3_M 1419 10.1950 24.08 94.64 0.16
Q3_K_M 1516 20.7076 25.73 46.59 0.36
Q3_K_L 1628 20.6384 27.63 46.75 0.36
IQ4_XS 1658 9.9013 28.14 97.45 0.15
IQ4_NL 1740 9.8926 29.53 97.53 0.15
Q4_0 1743 10.0757 29.58 95.76 0.16
Q4_K_S 1749 9.8497 29.68 97.96 0.15
Q4_K_M 1840 9.8160 31.23 98.29 0.15
Q4_1 1903 9.8176 32.30 98.28 0.15
Q5_K_S 2069 9.7456 35.12 99.00 0.15
Q5_0 2074 9.7237 35.20 99.23 0.15
Q5_K_M 2121 9.7331 36.00 99.13 0.15
Q5_1 2234 9.7260 37.92 99.20 0.15
Q6_K 2420 9.6939 41.07 99.53 0.15
Q8_0 3133 9.6710 53.17 99.77 0.15
F16 5892 9.6486 100 100 0.15