GalaxDB Cloud·Managed AI database. Local embeddings, time-travel, training export.Coming soon.Free tier. No credit card.

// BENCHMARKS

Real numbers. Real hardware.

Every number on this page was measured on real hardware with --release builds. Random-vector benchmarks are not reported. Commands to reproduce every result are shown inline.

Hardware: AWS c6id.4xlarge·Intel Xeon Platinum 8375C, 16 vCPU, 32 GiB RAM, 884 GB NVMe·Ubuntu 24.04, io_uring backend

HNSW Vector Search: SIFT-1M

Dataset: SIFT-1M: 1,000,000 x 128-dim float32 vectors, 10,000 queries, pre-computed ground truth. Source: ftp://ftp.irisa.fr/local/texmex/corpus/sift.tar.gz
SHA256: 92f1270c5e3a0cb46b89983e72b0511e4df065c31a9fa0276d8c9b1fca5bc81a

Build: M=16, ef_construction=200: 65.4s (15,295 vec/sec)

ef_search	recall@10	mean latency	p99 latency
10	0.756	57.7 µs	105 µs
50	0.959	156.7 µs	229 µs
100	0.983	266.7 µs	364 µs
200	0.990	458.9 µs	612 µs

# Reproduce

cargo build --release -p galaxdb-benchmarks

./target/release/galaxdb-sift-bench \

--dataset /path/to/sift \

--ef-search 10,50,100,200 \

--output bench-results/sift_bench.json

Storage Engine: durable write path

GalaxDB and PostgreSQL 16.14 run on the same instance-store NVMe (PostgreSQL's data directory relocated to the NVMe), fsync=on, both using prepared statements. An apples-to-apples comparison.

Concurrent INSERT vs PostgreSQL 16

Clients	GalaxDB	PostgreSQL 16
1	10,450 rows/s	11,891 rows/s
4	30,468 rows/s	34,298 rows/s
8	36,632 rows/s	54,432 rows/s
16	37,448 rows/s	84,747 rows/s

GalaxDB is competitive at low concurrency (0.88x PostgreSQL at 1 client, 0.89x at 4); PostgreSQL's mature process-per-connection model scales better past 8 concurrent clients (0.44x at 16). The remaining gap is the async server's per-query thread hand-off, not the storage engine itself.

# Reproduce

./target/release/concurrent-insert-bench --rows 5000 --clients 1,4,8,16 --pg-port 5432

Bulk load and engine write path

Path	Throughput	What it measures
COPY FROM STDIN (wire)	190,287 rows/s	bulk ingest, chunked group commit (25.97x vs row INSERT)
single-row INSERT (wire)	~8,525 rows/s	per-row roundtrip over the PostgreSQL protocol
put_sync (engine, 1 fsync/row)	~26,500 rows/s	strict per-row durability
put_batch_sync (engine, amortized)	~1.4 to 2.1M rows/s	in-memory path, fsync amortized over a batch

# Reproduce

./target/release/copy-bench --rows 200000

./target/release/single-row-insert-bench --rows 20000

./target/release/engine-microbench --max 200000

Encryption

Measured with cargo bench -p galaxdb-crypto on the same hardware.

Operation	Latency	Throughput
AEGIS-256 decrypt 1 MB	151 µs	6.63 GB/s
AEGIS-256 encrypt 64 KB	9.75 µs	6.56 GB/s
AES-256-GCM decrypt 1 MB	701 µs	1.43 GB/s
XXH3-64 checksum 1 MB	--	34.1 GB/s
ART lookup (1M keys)	168 ns/op	--

Crash Safety

All 7 chaos scenarios pass in under 30s total.

Scenario	Result	Time
Kill mid-flush: WAL replay	1,000 rows recovered, zero loss	8.79s
Kill mid-compaction: old blocks intact	4,000 keys readable	0.02s
Corrupt WAL record: replay stops at corruption	Partial recovery, no corrupt data returned	1.81s
Disk full: clean checkpoint, writes blocked	Reserve file freed, reads continue	0.01s
Kill sidecar: backlog preserved, no data loss	50 requests queued, drained on recovery	0.00s
100 concurrent writers	100K writes, 0 duplicates, 0 missing	0.13s
OLAP scan during OLTP	0 HotSet evictions, OLTP p99 unaffected	0.15s
Total	7 passed / 0 failed	10.91s

# Reproduce

cargo run --release -p galaxdb-chaos-tests

Test Suite

823

Rust tests

0 failed, release build

Chaos scenarios

0 failed

10.91s

Total chaos time

all recovery < 30s

# Reproduce

cargo test --release --lib

Methodology

-All numbers measured on AWS c6id.4xlarge (Intel Xeon Platinum 8375C, 16 vCPU, 32 GiB RAM, 884 GB NVMe), Ubuntu 24.04.
-All builds use cargo build --release. Debug builds are never published.
-Random-vector HNSW benchmarks are not reported. SIFT-1M only.
-Full reproduction guide and raw provenance JSON: BENCHMARKS.md