Upload perplexity.md
f0ebb22
verified
Quant |
Size (MB) |
PPL |
Size (%) |
Accuracy (%) |
PPL error rate |
IQ1_S |
301 |
32.6390 |
31.75 |
69.27 |
0.59 |
IQ1_M |
303 |
29.9721 |
31.96 |
75.43 |
0.53 |
IQ2_XXS |
306 |
28.2728 |
32.28 |
79.97 |
0.52 |
IQ2_XS |
309 |
26.5764 |
32.59 |
85.07 |
0.48 |
IQ2_S |
310 |
26.3276 |
32.70 |
85.88 |
0.48 |
IQ2_M |
313 |
25.6364 |
33.02 |
88.19 |
0.46 |
Q2_K_S |
315 |
25.6897 |
33.23 |
88.01 |
0.46 |
IQ3_XXS |
318 |
24.6070 |
33.54 |
91.88 |
0.44 |
Q3_K_S |
322 |
24.5354 |
33.97 |
92.15 |
0.44 |
IQ3_S |
322 |
24.0335 |
33.97 |
94.07 |
0.43 |
IQ3_XS |
322 |
24.0335 |
33.97 |
94.07 |
0.43 |
Q2_K |
322 |
24.4565 |
33.97 |
92.45 |
0.44 |
IQ3_M |
326 |
23.8652 |
34.39 |
94.74 |
0.43 |
IQ4_XS |
333 |
23.6261 |
35.13 |
95.70 |
0.42 |
IQ4_NL |
336 |
23.6102 |
35.44 |
95.76 |
0.42 |
Q4_0 |
336 |
23.8547 |
35.44 |
94.78 |
0.42 |
Q3_K_M |
338 |
23.5268 |
35.65 |
96.10 |
0.42 |
Q3_K_L |
352 |
23.3214 |
37.13 |
96.95 |
0.42 |
Q4_1 |
357 |
23.3396 |
37.66 |
96.87 |
0.42 |
Q4_K_S |
367 |
23.2008 |
38.71 |
97.45 |
0.41 |
Q5_0 |
379 |
23.1914 |
39.98 |
97.49 |
0.41 |
Q4_K_M |
379 |
23.1306 |
39.98 |
97.75 |
0.41 |
Q5_K_S |
393 |
22.8146 |
41.46 |
99.10 |
0.41 |
Q5_1 |
399 |
22.8381 |
42.09 |
99.00 |
0.41 |
Q5_K_M |
400 |
22.7761 |
42.19 |
99.27 |
0.41 |
Q6_K |
482 |
22.6302 |
50.84 |
99.91 |
0.40 |
Q8_0 |
506 |
22.6359 |
53.38 |
99.88 |
0.40 |
F16 |
948 |
22.6094 |
100 |
100 |
0.40 |