All Products
Search
Document Center

Hologres:Vector search instance specs

Last Updated:Mar 26, 2026

High-performance vector searches depend on vector indexes and impose requirements on instance memory. Use this page to find the minimum instance size for your vector dataset, based on its dimension count and row count.

The specifications below apply to in-memory indexes only. If you use an HGraph index with precise_io_type set to reader_io (a hybrid memory and disk index), the same instance can support more vector data.

Recommended minimum instance specifications

Find your dimension in the left column, then read across to the row-count range that matches your dataset. The table covers single-table scenarios. Test against your actual queries per second (QPS) and latency targets, and increase the instance size if needed.

Vector dimensionRow countMinimum instance
128Less than 200 million32 CPU cores
128200 million to 400 million64 CPU cores
128More than 400 million128 CPU cores or above
256Less than 60 million32 CPU cores
25660 million to 120 million64 CPU cores
256More than 120 million128 CPU cores or above
512Less than 30 million32 CPU cores
51230 million to 64 million64 CPU cores
512More than 64 million128 CPU cores or above
768Less than 24 million32 CPU cores
76824 million to 48 million64 CPU cores
768More than 48 million128 CPU cores or above
1024Less than 16 million32 CPU cores
102416 million to 32 million64 CPU cores
1024More than 32 million128 CPU cores or above
1536Less than 10 million32 CPU cores
153610 million to 20 million64 CPU cores
1536More than 20 million128 CPU cores or above

Worked example: If you have 30 million 768-dimension vectors, the table shows a gap between the 24-million (32 cores) and 48-million (64 cores) thresholds. Start with 64 CPU cores and validate against your QPS and latency targets before scaling further.

For exact-match vector searches, no vector index is required. Scale your instance based on the table above using your row count and dimension.