32 lines
2.2 KiB
CSV
32 lines
2.2 KiB
CSV
model,thinking,grammar,concurrency,requests,ttft_mean,ttft_std,dur_mean,dur_std,tps_mean,tps_std
|
|
Qwen3.5-4B-4bit,on,none,1,65,0.047,0.000,0.933,0.023,137.316,3.228
|
|
Qwen3.5-4B-4bit,on,none,2,88,0.074,0.019,1.369,0.061,93.691,4.808
|
|
Qwen3.5-4B-4bit,on,none,4,129,0.139,0.047,1.869,0.097,68.775,5.675
|
|
Qwen3.5-4B-4bit,on,json,1,53,0.055,0.007,1.153,0.051,110.527,2.933
|
|
Qwen3.5-4B-4bit,on,json,2,83,0.072,0.010,1.462,0.067,87.131,2.908
|
|
Qwen3.5-4B-4bit,on,json,4,112,0.129,0.053,2.203,0.093,57.827,1.513
|
|
Qwen3.5-4B-4bit,off,none,1,60,0.062,0.000,1.003,0.021,127.639,2.577
|
|
Qwen3.5-4B-4bit,off,none,2,92,0.084,0.021,1.322,0.018,96.836,1.343
|
|
Qwen3.5-4B-4bit,off,none,4,116,0.155,0.042,2.085,0.029,61.399,0.867
|
|
Qwen3.5-4B-4bit,off,json,1,50,0.057,0.005,1.205,0.023,106.265,2.022
|
|
Qwen3.5-4B-4bit,off,json,2,80,0.094,0.024,1.502,0.023,85.265,1.313
|
|
Qwen3.5-4B-4bit,off,json,4,108,0.141,0.046,2.272,0.032,56.331,0.776
|
|
gemma-3-4b-it-qat-4bit,off,none,1,64,0.052,0.000,0.945,0.018,135.489,2.631
|
|
gemma-3-4b-it-qat-4bit,off,none,2,96,0.075,0.006,1.256,0.019,101.952,1.533
|
|
gemma-3-4b-it-qat-4bit,off,none,4,124,0.136,0.035,1.979,0.036,64.715,1.176
|
|
gemma-3-4b-it-qat-4bit,off,json,1,54,0.052,0.005,1.123,0.017,114.054,1.710
|
|
gemma-3-4b-it-qat-4bit,off,json,2,86,0.079,0.015,1.398,0.020,91.553,1.284
|
|
gemma-3-4b-it-qat-4bit,off,json,4,116,0.150,0.024,2.112,0.027,60.616,0.772
|
|
gpt-oss-20b-MXFP4-Q4,on,none,1,19,0.196,0.017,3.288,0.075,121.709,2.734
|
|
gpt-oss-20b-MXFP4-Q4,on,none,2,24,0.385,0.040,5.016,0.023,79.747,0.360
|
|
gpt-oss-20b-MXFP4-Q4,on,none,4,32,0.708,0.095,8.497,0.068,47.081,0.379
|
|
gpt-oss-20b-MXFP4-Q4,on,json,1,17,0.190,0.000,3.580,0.021,111.724,0.648
|
|
gpt-oss-20b-MXFP4-Q4,on,json,2,22,0.395,0.041,5.482,0.020,72.970,0.270
|
|
gpt-oss-20b-MXFP4-Q4,on,json,4,28,0.739,0.098,8.960,0.281,44.688,1.410
|
|
gpt-oss-20b-MXFP4-Q4,off,none,1,20,0.186,0.000,3.071,0.027,130.262,1.162
|
|
gpt-oss-20b-MXFP4-Q4,off,none,2,26,0.415,0.087,4.959,0.329,80.970,4.954
|
|
gpt-oss-20b-MXFP4-Q4,off,none,4,28,0.745,0.102,9.027,0.091,44.314,0.443
|
|
gpt-oss-20b-MXFP4-Q4,off,json,1,6,0.214,0.000,3.822,0.033,104.671,0.896
|
|
gpt-oss-20b-MXFP4-Q4,off,json,2,10,0.280,0.059,5.850,0.239,68.488,2.962
|
|
gpt-oss-20b-MXFP4-Q4,off,json,4,10,0.375,0.152,10.262,0.939,39.272,3.572
|