Benchmark methodology
The numbers. And everything behind them.
The front-page RSS result comes from a defined core-engine test that anyone with the source tree can run.
This page documents exactly what that test does, what it measures, what it deliberately does not measure, and how to reproduce it. The test ships with Meivo itself: crates/gm-server/tests/ram_regression.rs.
What is measured
Peak RSS(resident set size, the physical RAM a process actually occupies) of a single process running Meivo's full ingestion path, while it ingests 51.2 MB of text. RSS is read with the memory-stats crate.
The corpus: deterministic by construction
The test generates 1,000 documents of roughly 50 KB each, 51.2 MB total, from a fixed 115-word vocabulary. Randomness comes from a seeded xorshift64* generator with the constant seed 0x6772_6561_746D_656D ("greatmem" in ASCII), so every run ingests the byte-identical corpus.
The system under test: the real pipeline
Nothing is mocked. The test wires up the same components the server uses.
BGE-small-en-v1.5 via fastembed / ONNX Runtime, one model instance behind the bounded batch queue.Sampling and assertions
RSS is sampled every 50 documents and once more after the pipeline drains. The test then asserts three things:
The same test runs in CI on every push to main. If that tested workload crosses the threshold, the build breaks.
The published run
The numbers on the front page come from a release-mode run on 2026-06-12: Apple M1 Pro, 16 GB RAM, macOS, total duration 2,620 seconds. Peak RSS was 588.1 MB. From 2.6 MB ingested to 51.2 MB ingested, sampled RSS ranged from 494.9 MB to 588.1 MB. These measurements describe this run and workload.
The idle figure
The 19 MB idle server number is rss_bytes reported by GET /v1/stats right after booting the published 158 MB Docker image, before the embedding model is loaded.
Honest limitations
Reproduce it
# from the Meivo source tree cargo test -p gm-server --release -- --ignored ram_regression --nocapture
Requirements: Rust stable, roughly 150 MB of disk for the first model download, and patience. Expect tens of minutes on CPU.
Raw output of the published run
[ram_regression] docs= 50 ingested= 2.6 MB rss= 535.9 MB peak= 535.9 MB [ram_regression] docs= 100 ingested= 5.1 MB rss= 530.5 MB peak= 535.9 MB [ram_regression] docs= 150 ingested= 7.7 MB rss= 529.3 MB peak= 535.9 MB [ram_regression] docs= 200 ingested= 10.2 MB rss= 535.8 MB peak= 535.9 MB [ram_regression] docs= 250 ingested= 12.8 MB rss= 512.6 MB peak= 535.9 MB [ram_regression] docs= 300 ingested= 15.4 MB rss= 578.1 MB peak= 578.1 MB [ram_regression] docs= 350 ingested= 17.9 MB rss= 545.5 MB peak= 578.1 MB [ram_regression] docs= 400 ingested= 20.5 MB rss= 547.7 MB peak= 578.1 MB [ram_regression] docs= 450 ingested= 23.1 MB rss= 520.9 MB peak= 578.1 MB [ram_regression] docs= 500 ingested= 25.6 MB rss= 545.8 MB peak= 578.1 MB [ram_regression] docs= 550 ingested= 28.2 MB rss= 550.6 MB peak= 578.1 MB [ram_regression] docs= 600 ingested= 30.7 MB rss= 543.4 MB peak= 578.1 MB [ram_regression] docs= 650 ingested= 33.3 MB rss= 556.5 MB peak= 578.1 MB [ram_regression] docs= 700 ingested= 35.9 MB rss= 543.7 MB peak= 578.1 MB [ram_regression] docs= 750 ingested= 38.4 MB rss= 530.4 MB peak= 578.1 MB [ram_regression] docs= 800 ingested= 41.0 MB rss= 526.9 MB peak= 578.1 MB [ram_regression] docs= 850 ingested= 43.6 MB rss= 494.9 MB peak= 578.1 MB [ram_regression] docs= 900 ingested= 46.1 MB rss= 560.0 MB peak= 578.1 MB [ram_regression] docs= 950 ingested= 48.7 MB rss= 588.1 MB peak= 588.1 MB [ram_regression] docs=1000 ingested= 51.2 MB rss= 541.3 MB peak= 588.1 MB [ram_regression] SUMMARY: ingested 51.2 MB across 1000 docs -> 31000 chunks; peak RSS 588.1 MB (limit 1024 MB) test ram_regression_50mb_ingest_stays_under_1gb ... ok test result: ok. 1 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 2619.96s