Faiss

Faiss is developed by Meta/Facebook. Faiss is a library for efficient similarity search and clustering of dense vectors.


Faiss 1.7.4

Test: demo_sift1M

OpenBenchmarking.org metrics for this test profile configuration based on 28 public results since 28 April 2023 with the latest data as of 8 January 2024.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Details
Percentile Rank
# Compatible Public Results
Seconds (Average)
Zen 4 [16 Cores / 32 Threads]
61st
3
64
Median
50th
77
Raptor Lake [24 Cores / 32 Threads]
43rd
4
79 +/- 2
Tiger Lake [4 Cores / 8 Threads]
33rd
3
86
Low-Tier
25th
> 95
Alder Lake [14 Cores / 20 Threads]
18th
3
98 +/- 6
Zen 4 [16 Cores / 32 Threads]
11th
4
102 +/- 2