← all runs
Cohere-100M — 2026-07-16
r8i.8xlarge · peak recall 0.9969 @ 28 QPS
“resized: 100M dataset build on 24xlarge downsized to 8xlarge”
QPS at recall
| Recall | Meerkat | pgvector HNSW (halfvec) | Δ vs best competitor |
|---|
| 0.90 | 558 | 100 | +458% |
| 0.95 | 272 | 72 | +276% |
| 0.99 | 62 | — (max r=0.986) | — |
Latency at recall
| Meerkat | pgvector HNSW (halfvec) | Δ vs best competitor |
|---|
| @ recall 0.90 | | | |
| p50 | 1.77 ms | 8.41 ms | -79% |
| p95 | 2.26 ms | 19.28 ms | -88% |
| p99 | 2.63 ms | 24.97 ms | -89% |
| @ recall 0.95 | | | |
| p50 | 3.61 ms | 14.19 ms | -75% |
| p95 | 4.48 ms | 17.51 ms | -74% |
| p99 | 5.42 ms | 19.87 ms | -73% |
| @ recall 0.99 | | | |
| p50 | 15.98 ms | — | — |
| p95 | 19.15 ms | — | — |
| p99 | 24.32 ms | — | — |
All values are taken at exactly the stated recall: each configuration's own sweep is log-interpolated between its two surrounding measured points (measured values are used verbatim on an exact hit) and the best configuration at that recall is shown — values are never interpolated across different configurations. “—” means no single sweep spans that recall; nothing is extrapolated. Recall is distance-based (ann-benchmarks, tie-aware). Insert/update/delete workloads are not measured.
Interpolated on config — Meerkat @0.90: mkt-defaults · pgvector HNSW (halfvec) @0.90: hnsw-m24-halfvec · Meerkat @0.95: mkt-defaults · pgvector HNSW (halfvec) @0.95: hnsw-m24-halfvec · Meerkat @0.99: mkt-defaults
Build comparison
| Meerkat | pgvector HNSW (halfvec) | Δ vs best competitor |
|---|
| Build time | 3443 s | 22212 s | -85% |
| Index size | 24.9 GB | 179.2 GB | -86% |
Build stats are for the configuration backing each column's best operating point: Meerkat = mkt-defaults, prewarmed · pgvector HNSW (halfvec) = hnsw-m24-halfvec, prewarmed.
Plots
Pareto svg ·
Distance-recall svg ·
Per-config svg ·
Build times svg ·
Index sizes svgHost
| Instance type | r8i.8xlarge |
| Hostname | ip-172-31-75-2 |
| CPU | Intel(R) Xeon(R) 6975P-C (32 vCPU) |
| Memory | 248 GB |
| OS | Ubuntu 26.04 LTS |
| Kernel | 7.0.0-1008-aws |
Versions
| rekall | 0.1.0 (c1f5545 / main) |
| PostgreSQL | PostgreSQL 18.4 (Ubuntu 18.4-1.pgdg26.04+1) on x86_64-pc-linux-gnu, compiled by gcc (Ubuntu 15.2.0-16ubuntu1) 15.2.0, 64-bit |
| meerkat | 0.1.0 (1f3ad94) |
| pg_prewarm | 1.2 |
| vector | 0.8.5 |
Search
Index builds
| Index | Type | Build time | Size | Workers |
|---|
| hnsw-m24-halfvec | pgvector-hnsw | 22212.1s | 179.2 GB | 32 |
| mkt-defaults | meerkat | 3442.7s | 24.9 GB | 32 |
Index parameters
hnsw-m24-halfvec: {"ef_construction":200,"encoding":"halfvec","m":24}
mkt-defaults: {"boundary_epsilon":null,"centroid_compression":null,"centroid_fastscan":null,"fan_out":null,"fastscan":null,"fastscan_bits":null,"nlist":null,"rerank_vectors":null,"soar_lambda":null}
PostgreSQL settings
effective_cache_size = 192 GB
effective_io_concurrency = 256
huge_pages = try
maintenance_work_mem = 102 GB
max_connections = 100
max_parallel_maintenance_workers = 16
max_parallel_workers = 32
random_page_cost = 1.1
shared_buffers = 64 GB
wal_level = replica
work_mem = 1 GB
