Cohere-100M — 2026-07-10

r8i.24xlarge · peak recall 0.9934 @ 36 QPS

“Higher boundary_replication”

Plots

Pareto svg · Distance-recall svg · Per-config svg · Build times svg

Host

Instance type	r8i.24xlarge
Hostname	ip-172-31-67-47
CPU	Intel(R) Xeon(R) 6975P-C (96 vCPU)
Memory	744 GB
OS	Ubuntu 26.04 LTS
Kernel	7.0.0-1008-aws

Versions

rekall	0.1.0 (8e82712 / 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 (ca8d3c9)
pg_prewarm	1.2
vector	0.8.4

Search

k	10
runs	3
warmup	500
num_queries	10000
S3 archive	s3://rekall-bench/runs/cohere-100m/2026-07-10/r8i.24xlarge-233117/

Index builds

Index	Type	Build time	Size	Workers
hnsw-m24-halfvec	pgvector-hnsw	21987.2s	179.2 GB	32
mkt-n400000-cctrue-fs16-soar-cfs	meerkat	11575.5s	20.2 GB	32
mkt-n400000-cctrue-fs16-soar-cfs-eps015	meerkat	3438.8s	23.8 GB	32

Index parameters

hnsw-m24-halfvec: {"ef_construction":200,"encoding":"halfvec","m":24}
mkt-n400000-cctrue-fs16-soar-cfs: {"boundary_epsilon":0.05,"centroid_compression":true,"centroid_fastscan":true,"fan_out":null,"fastscan":true,"fastscan_bits":null,"nlist":400000,"rerank_vectors":null,"soar_lambda":1.0}
mkt-n400000-cctrue-fs16-soar-cfs-eps015: {"boundary_epsilon":0.15,"centroid_compression":true,"centroid_fastscan":true,"fan_out":null,"fastscan":true,"fastscan_bits":null,"nlist":400000,"rerank_vectors":null,"soar_lambda":1.0}

PostgreSQL settings

effective_cache_size = 576 GB
effective_io_concurrency = 256
huge_pages = try
maintenance_work_mem = 307 GB
max_connections = 100
max_parallel_maintenance_workers = 32
max_parallel_workers = 96
random_page_cost = 1.1
shared_buffers = 192 GB
wal_level = replica
work_mem = 1 GB