11Topology,Precision,Input Size,1st latency (ms),2nd latency (ms),max rss memory,2nd token per sec
2- dolly-v2-3b,INT4-MIXED,32,70.8,23.6,3580.5,42.37,,,
3- gemma-2b-it,INT4-MIXED,32,58.8,24,4086.6,41.67,,,
4- phi-2,INT4-MIXED,32,67.9,24.1,3782.8,41.49,,,
5- gemma-2b-it,INT4-MIXED,1024,712.9,24.8,4186.5,40.32,,,
6- gemma-2b-it,INT4-MIXED,4096,3135.2,25.3,4931.5,39.53,,,
7- stable-zephyr-3b-dpo,INT4-MIXED,32,76.3,25.4,3810.1,39.37,,,
8- gemma-2b-it,INT4-MIXED,2048,1440,25.5,4250,39.22,,,
9- dolly-v2-3b,INT4-MIXED,1024,1068.1,26.4,4119.8,37.88,,,
10- phi-2,INT4-MIXED,1024,1043,27,4328.3,37.04,,,
11- stablelm-3b-4e1t,INT4-MIXED,32,68.5,27.9,3439.8,35.84,,,
12- stable-zephyr-3b-dpo,INT4-MIXED,1024,1051.4,28.3,4325.2,35.34,,,
13- stable-zephyr-3b-dpo,INT4-MIXED,2076,2677.9,31.1,4992.6,32.15,,,
14- stablelm-3b-4e1t,INT4-MIXED,1024,1057.3,31.1,4182.4,32.15,,,
15- phi-3-mini-4k-instruct,INT4-MIXED,32,94.5,32.3,4263.6,30.96,,,
16- stablelm-3b-4e1t,INT4-MIXED,2048,2564,33.7,5129.6,29.67,,,
17- phi-3-mini-4k-instruct,INT4-MIXED,1024,1366,35.9,4642.7,27.86,,,
18- phi-3-mini-4k-instruct,INT4-MIXED,2048,3183,38.9,5685.2,25.71,,,
19- stable-zephyr-3b-dpo,INT8-CW,32,84.6,39.2,4402.8,25.51,,,
20- stablelm-3b-4e1t,INT4-MIXED,4096,6621.6,39.2,7302,25.51,,,
21- stablelm-3b-4e1t,INT8-CW,32,82.9,39.3,4315.5,25.45,,,
22- gemma-2b-it,INT8-CW,32,85.4,39.5,4886.5,25.32,,,
23- phi-2,INT8-CW,32,95,40.1,4447.6,24.94,,,
24- gemma-2b-it,INT8-CW,1024,791.5,40.2,4847.7,24.88,,,
25- dolly-v2-3b,INT8-CW,32,93.6,40.4,4614.8,24.75,,,
26- gemma-2b-it,INT8-CW,4096,3371.3,40.6,5799.9,24.63,,,
27- gemma-2b-it,INT8-CW,2048,1594.2,40.9,5115.9,24.45,,,
28- stable-zephyr-3b-dpo,INT8-CW,1024,1177.2,42.1,5124.4,23.75,,,
29- stablelm-3b-4e1t,INT8-CW,1024,1174.4,42.3,5037,23.64,,,
30- phi-2,INT8-CW,1024,1145.9,43,5183.6,23.26,,,
31- dolly-v2-3b,INT8-CW,1024,1171.3,43.3,5172.3,23.09,,,
32- stable-zephyr-3b-dpo,INT8-CW,2076,4070,44.8,5927.9,22.32,,,
33- stablelm-3b-4e1t,INT8-CW,2048,2797.1,44.8,5950,22.32,,,
34- phi-3-mini-4k-instruct,INT4-MIXED,4096,8047.2,45.1,8019.5,22.17,,,
35- gpt-j-6b,INT4-MIXED,32,136,48.1,5306.2,20.79,,,
36- flan-t5-xxl,INT4-MIXED,33,79.3,48.2,14071,20.75,,,
37- chatglm3-6b,INT4-MIXED,32,147.4,48.7,5063.6,20.53,,,
38- chatglm3-6b,INT4-MIXED,1024,1877.2,50.1,5267.6,19.96,,,
39- stablelm-3b-4e1t,INT8-CW,4096,7094.2,50.1,8047.9,19.96,,,
40- chatglm3-6b,INT4-MIXED,2048,4009.4,51.4,5677,19.46,,,
41- chatglm3-6b,INT4-MIXED,4096,8779.6,51.5,7111.5,19.42,,,
42- flan-t5-xxl,INT4-MIXED,1139,376.5,52,15851.9,19.23,,,
43- gpt-j-6b,INT4-MIXED,1024,2112.5,52.2,6915.4,19.16,,,
44- phi-3-mini-4k-instruct,INT8-CW,32,101.5,53,5272.3,18.87,,,
45- falcon-7b-instruct,INT4-MIXED,32,172.6,55.7,5732.4,17.95,,,
46- gpt-j-6b,INT4-MIXED,2048,4759.6,56.2,9203.4,17.79,,,
47- phi-3-mini-4k-instruct,INT8-CW,1024,1556.7,56.4,6118,17.73,,,
48- flan-t5-xxl,INT4-MIXED,2048,664,56.7,20616.4,17.64,,,
49- falcon-7b-instruct,INT4-MIXED,1024,2316,57.1,6052.5,17.51,,,
50- phi-3-mini-4k-instruct,INT8-CW,2048,3593.9,59.3,7165.8,16.86,,,
51- mistral-7b-v0.1,INT4-MIXED,32,180,61,5781.8,16.39,,,
52- mistral-7b-v0.1,INT4-MIXED,1024,2311.4,63.2,6227,15.82,,,
53- mistral-7b-v0.1,INT4-MIXED,2048,4931.2,65.2,6883.6,15.34,,,
54- phi-3-mini-4k-instruct,INT8-CW,4096,8851,65.4,9741.2,15.29,,,
55- zephyr-7b-beta,INT4-MIXED,32,172,65.7,6387.4,15.22,,,
56- mistral-7b-v0.1,INT4-MIXED,4096,10822.1,66.1,8790.2,15.13,,,
57- baichuan2-7b-chat,INT4-MIXED,32,155.4,66.7,6847.8,14.99,,,
58- flan-t5-xxl,INT4-MIXED,4096,1368.2,67.5,30669.4,14.81,,,
59- zephyr-7b-beta,INT4-MIXED,1024,2313.7,67.8,6530.2,14.75,,,
60- gemma-7b-it,INT4-MIXED,32,231.5,68.8,7265.1,14.53,,,
61- gemma-2b-it,FP16,32,91.8,69.1,7829.9,14.47,,,
62- gemma-2b-it,FP16,1024,1398.2,69.9,7656.5,14.31,,,
63- gemma-2b-it,FP16,2048,2977.5,70.7,7982.2,14.14,,,
64- baichuan2-7b-chat,INT4-MIXED,1024,2771.3,71,7753.8,14.08,,,
65- phi-2,FP16,32,99.8,71.1,7066.5,14.06,,,
66- gemma-2b-it,FP16,4096,6309.8,71.2,8607.5,14.04,,,
67- stable-zephyr-3b-dpo,FP16,32,94.7,71.3,7072.5,14.03,,,
68- stablelm-3b-4e1t,FP16,32,94.5,71.3,6980.7,14.03,,,
69- dolly-v2-3b,FP16,32,98.8,71.6,7211,13.97,,,
70- gemma-7b-it,INT4-MIXED,1024,2832,72.8,8247.3,13.74,,,
71- baichuan2-7b-chat,INT4-MIXED,2048,5351.1,75.1,9136.2,13.32,,,
72- phi-2,FP16,1024,1376.9,75.7,8097.9,13.21,,,
73- stable-zephyr-3b-dpo,FP16,1024,1375.4,75.8,8106.4,13.19,,,
74- stablelm-3b-4e1t,FP16,1024,1382.8,75.8,8020.3,13.19,,,
75- dolly-v2-3b,FP16,1024,1405.3,76.3,8093.4,13.11,,,
76- qwen-7b-chat,INT4-MIXED,32,145.9,76.4,7648.4,13.09,,,
77- gemma-7b-it,INT4-MIXED,2048,6079.5,77,9493.9,12.99,,,
78- stablelm-3b-4e1t,FP16,2048,3170.1,80.3,9339.1,12.45,,,
79- stable-zephyr-3b-dpo,FP16,2076,9419.9,80.4,9101,12.44,,,
80- qwen-7b-chat,INT4-MIXED,1024,2405.7,80.7,8483.9,12.39,,,
81- gpt-j-6b,INT8-CW,32,142.1,81.9,7614,12.21,,,
82- baichuan2-7b-chat,INT4-MIXED,3968,12508.6,83.2,9938,12.02,,,
83- flan-t5-xxl,INT8-CW,33,123.9,83.2,23446.4,12.02,,,
84- gemma-7b-it,INT4-MIXED,4096,14292.9,84.9,11672.5,11.78,,,
85- qwen-7b-chat,INT4-MIXED,2048,5429.1,85.2,9822.4,11.74,,,
86- chatglm3-6b,INT8-CW,32,143,85.4,7618.1,11.71,,,
87- gpt-j-6b,INT8-CW,1024,2307.9,86.1,9248.2,11.61,,,
88- chatglm3-6b,INT8-CW,1024,2472.9,86.8,7824.2,11.52,,,
89- flan-t5-xxl,INT8-CW,1139,471,86.8,25692.8,11.52,,,
90- chatglm3-6b,INT8-CW,2048,5232.6,88,8354.6,11.36,,,
91- chatglm3-6b,INT8-CW,4096,11328.1,88.1,9675.8,11.35,,,
92- stablelm-3b-4e1t,FP16,4096,7736.9,89.1,12203.8,11.22,,,
93- gpt-j-6b,INT8-CW,2048,5140,90.2,11542.2,11.09,,,
94- flan-t5-xxl,INT8-CW,2048,804.4,91.4,30371.1,10.94,,,
95- falcon-7b-instruct,INT8-CW,32,171.9,93.7,8415.5,10.67,,,
96- qwen-7b-chat,INT4-MIXED,4096,13230.6,93.7,12824.2,10.67,,,
97- falcon-7b-instruct,INT8-CW,1024,2564.1,95.1,8741.2,10.52,,,
98- phi-3-mini-4k-instruct,FP16,32,121.4,98.8,9057.3,10.12,,,
99- baichuan2-7b-chat,INT8-CW,32,152,99.3,9002,10.07,,,
2+ dolly-v2-3b,INT4-MIXED,32,70.8,23.6,3580.5,42.37
3+ gemma-2b-it,INT4-MIXED,32,58.8,24,4086.6,41.67
4+ phi-2,INT4-MIXED,32,67.9,24.1,3782.8,41.49
5+ gemma-2b-it,INT4-MIXED,1024,712.9,24.8,4186.5,40.32
6+ gemma-2b-it,INT4-MIXED,4096,3135.2,25.3,4931.5,39.53
7+ stable-zephyr-3b-dpo,INT4-MIXED,32,76.3,25.4,3810.1,39.37
8+ gemma-2b-it,INT4-MIXED,2048,1440,25.5,4250,39.22
9+ dolly-v2-3b,INT4-MIXED,1024,1068.1,26.4,4119.8,37.88
10+ phi-2,INT4-MIXED,1024,1043,27,4328.3,37.04
11+ stablelm-3b-4e1t,INT4-MIXED,32,68.5,27.9,3439.8,35.84
12+ stable-zephyr-3b-dpo,INT4-MIXED,1024,1051.4,28.3,4325.2,35.34
13+ stable-zephyr-3b-dpo,INT4-MIXED,2076,2677.9,31.1,4992.6,32.15
14+ stablelm-3b-4e1t,INT4-MIXED,1024,1057.3,31.1,4182.4,32.15
15+ phi-3-mini-4k-instruct,INT4-MIXED,32,94.5,32.3,4263.6,30.96
16+ stablelm-3b-4e1t,INT4-MIXED,2048,2564,33.7,5129.6,29.67
17+ phi-3-mini-4k-instruct,INT4-MIXED,1024,1366,35.9,4642.7,27.86
18+ phi-3-mini-4k-instruct,INT4-MIXED,2048,3183,38.9,5685.2,25.71
19+ stable-zephyr-3b-dpo,INT8-CW,32,84.6,39.2,4402.8,25.51
20+ stablelm-3b-4e1t,INT4-MIXED,4096,6621.6,39.2,7302,25.51
21+ stablelm-3b-4e1t,INT8-CW,32,82.9,39.3,4315.5,25.45
22+ gemma-2b-it,INT8-CW,32,85.4,39.5,4886.5,25.32
23+ phi-2,INT8-CW,32,95,40.1,4447.6,24.94
24+ gemma-2b-it,INT8-CW,1024,791.5,40.2,4847.7,24.88
25+ dolly-v2-3b,INT8-CW,32,93.6,40.4,4614.8,24.75
26+ gemma-2b-it,INT8-CW,4096,3371.3,40.6,5799.9,24.63
27+ gemma-2b-it,INT8-CW,2048,1594.2,40.9,5115.9,24.45
28+ stable-zephyr-3b-dpo,INT8-CW,1024,1177.2,42.1,5124.4,23.75
29+ stablelm-3b-4e1t,INT8-CW,1024,1174.4,42.3,5037,23.64
30+ phi-2,INT8-CW,1024,1145.9,43,5183.6,23.26
31+ dolly-v2-3b,INT8-CW,1024,1171.3,43.3,5172.3,23.09
32+ stable-zephyr-3b-dpo,INT8-CW,2076,4070,44.8,5927.9,22.32
33+ stablelm-3b-4e1t,INT8-CW,2048,2797.1,44.8,5950,22.32
34+ phi-3-mini-4k-instruct,INT4-MIXED,4096,8047.2,45.1,8019.5,22.17
35+ gpt-j-6b,INT4-MIXED,32,136,48.1,5306.2,20.79
36+ flan-t5-xxl,INT4-MIXED,33,79.3,48.2,14071,20.75
37+ chatglm3-6b,INT4-MIXED,32,147.4,48.7,5063.6,20.53
38+ chatglm3-6b,INT4-MIXED,1024,1877.2,50.1,5267.6,19.96
39+ stablelm-3b-4e1t,INT8-CW,4096,7094.2,50.1,8047.9,19.96
40+ chatglm3-6b,INT4-MIXED,2048,4009.4,51.4,5677,19.46
41+ chatglm3-6b,INT4-MIXED,4096,8779.6,51.5,7111.5,19.42
42+ flan-t5-xxl,INT4-MIXED,1139,376.5,52,15851.9,19.23
43+ gpt-j-6b,INT4-MIXED,1024,2112.5,52.2,6915.4,19.16
44+ phi-3-mini-4k-instruct,INT8-CW,32,101.5,53,5272.3,18.87
45+ falcon-7b-instruct,INT4-MIXED,32,172.6,55.7,5732.4,17.95
46+ gpt-j-6b,INT4-MIXED,2048,4759.6,56.2,9203.4,17.79
47+ phi-3-mini-4k-instruct,INT8-CW,1024,1556.7,56.4,6118,17.73
48+ flan-t5-xxl,INT4-MIXED,2048,664,56.7,20616.4,17.64
49+ falcon-7b-instruct,INT4-MIXED,1024,2316,57.1,6052.5,17.51
50+ phi-3-mini-4k-instruct,INT8-CW,2048,3593.9,59.3,7165.8,16.86
51+ mistral-7b-v0.1,INT4-MIXED,32,180,61,5781.8,16.39
52+ mistral-7b-v0.1,INT4-MIXED,1024,2311.4,63.2,6227,15.82
53+ mistral-7b-v0.1,INT4-MIXED,2048,4931.2,65.2,6883.6,15.34
54+ phi-3-mini-4k-instruct,INT8-CW,4096,8851,65.4,9741.2,15.29
55+ zephyr-7b-beta,INT4-MIXED,32,172,65.7,6387.4,15.22
56+ mistral-7b-v0.1,INT4-MIXED,4096,10822.1,66.1,8790.2,15.13
57+ baichuan2-7b-chat,INT4-MIXED,32,155.4,66.7,6847.8,14.99
58+ flan-t5-xxl,INT4-MIXED,4096,1368.2,67.5,30669.4,14.81
59+ zephyr-7b-beta,INT4-MIXED,1024,2313.7,67.8,6530.2,14.75
60+ gemma-7b-it,INT4-MIXED,32,231.5,68.8,7265.1,14.53
61+ gemma-2b-it,FP16,32,91.8,69.1,7829.9,14.47
62+ gemma-2b-it,FP16,1024,1398.2,69.9,7656.5,14.31
63+ gemma-2b-it,FP16,2048,2977.5,70.7,7982.2,14.14
64+ baichuan2-7b-chat,INT4-MIXED,1024,2771.3,71,7753.8,14.08
65+ phi-2,FP16,32,99.8,71.1,7066.5,14.06
66+ gemma-2b-it,FP16,4096,6309.8,71.2,8607.5,14.04
67+ stable-zephyr-3b-dpo,FP16,32,94.7,71.3,7072.5,14.03
68+ stablelm-3b-4e1t,FP16,32,94.5,71.3,6980.7,14.03
69+ dolly-v2-3b,FP16,32,98.8,71.6,7211,13.97
70+ gemma-7b-it,INT4-MIXED,1024,2832,72.8,8247.3,13.74
71+ baichuan2-7b-chat,INT4-MIXED,2048,5351.1,75.1,9136.2,13.32
72+ phi-2,FP16,1024,1376.9,75.7,8097.9,13.21
73+ stable-zephyr-3b-dpo,FP16,1024,1375.4,75.8,8106.4,13.19
74+ stablelm-3b-4e1t,FP16,1024,1382.8,75.8,8020.3,13.19
75+ dolly-v2-3b,FP16,1024,1405.3,76.3,8093.4,13.11
76+ qwen-7b-chat,INT4-MIXED,32,145.9,76.4,7648.4,13.09
77+ gemma-7b-it,INT4-MIXED,2048,6079.5,77,9493.9,12.99
78+ stablelm-3b-4e1t,FP16,2048,3170.1,80.3,9339.1,12.45
79+ stable-zephyr-3b-dpo,FP16,2076,9419.9,80.4,9101,12.44
80+ qwen-7b-chat,INT4-MIXED,1024,2405.7,80.7,8483.9,12.39
81+ gpt-j-6b,INT8-CW,32,142.1,81.9,7614,12.21
82+ baichuan2-7b-chat,INT4-MIXED,3968,12508.6,83.2,9938,12.02
83+ flan-t5-xxl,INT8-CW,33,123.9,83.2,23446.4,12.02
84+ gemma-7b-it,INT4-MIXED,4096,14292.9,84.9,11672.5,11.78
85+ qwen-7b-chat,INT4-MIXED,2048,5429.1,85.2,9822.4,11.74
86+ chatglm3-6b,INT8-CW,32,143,85.4,7618.1,11.71
87+ gpt-j-6b,INT8-CW,1024,2307.9,86.1,9248.2,11.61
88+ chatglm3-6b,INT8-CW,1024,2472.9,86.8,7824.2,11.52
89+ flan-t5-xxl,INT8-CW,1139,471,86.8,25692.8,11.52
90+ chatglm3-6b,INT8-CW,2048,5232.6,88,8354.6,11.36
91+ chatglm3-6b,INT8-CW,4096,11328.1,88.1,9675.8,11.35
92+ stablelm-3b-4e1t,FP16,4096,7736.9,89.1,12203.8,11.22
93+ gpt-j-6b,INT8-CW,2048,5140,90.2,11542.2,11.09
94+ flan-t5-xxl,INT8-CW,2048,804.4,91.4,30371.1,10.94
95+ falcon-7b-instruct,INT8-CW,32,171.9,93.7,8415.5,10.67
96+ qwen-7b-chat,INT4-MIXED,4096,13230.6,93.7,12824.2,10.67
97+ falcon-7b-instruct,INT8-CW,1024,2564.1,95.1,8741.2,10.52
98+ phi-3-mini-4k-instruct,FP16,32,121.4,98.8,9057.3,10.12
99+ baichuan2-7b-chat,INT8-CW,32,152,99.3,9002,10.07
0 commit comments