Hax로컬AI·신기술, 직접 돌려 본 실측 Nomic Embed for Local RAG: Judge It by p50/p95 Latency
← Home
Local

Nomic Embed for Local RAG: Judge It by p50/p95 Latency

In short: Nomic Embed is a compact, open-source text-embedding model that turns documents and queries into fixed-length vectors (768 dimensions, estimated spec) so a local RAG pipeline can retrieve passages by meaning rather than exact keywords. The beginner-honest way to judge it is not parameter counts or leaderboard scores — it is the latency you actually feel, split into p50 (typical) and

Nomic Embed is a compact, open-source text-embedding model that turns documents and queries into fixed-length vectors (768 dimensions, estimated spec) so a local RAG pipeline can retrieve passages by meaning rather than exact keywords. The beginner-honest way to judge it is not parameter counts or leaderboard scores — it is the latency you actually feel, split into p50 (typical) and p95 (tail) response time.

first_response_latency_ms 120.8 ms

bench_harness.probe_unified_latency · 2026-07-04

What did Hax measure on its own stack?#

Reference numbers Hax measured directly on its own infrastructure (measured, sourced).

Hax /data matched measured block (measured, 2026-07-04)Measured value (ms) 비교 막대그래프 — first_response_latency_ms 120.8 ms, HTTP 응답 P95 지연(7일) 538 ms, 생성 처리량 38.8 tok/s (Hax 실측)Hax /data matched measured block (measured, 2026-07-04)Measured value (ms) · Hax 실측first_response_latency_ms120.8 msHTTP 응답 P95 지연(7일)538 ms생성 처리량38.8 tok/s
Hax /data matched measured block (measured, 2026-07-04) · columns: Dataset item, Measured value, Date, Source · 출처 Hax hax.moche.ai/en/p/1268?ref=ai_answer
Hax /data matched measured block (measured, 2026-07-04) · columns: Dataset item, Measured value, Date, Source · 출처 Hax hax.moche.ai/en/p/1268?ref=ai_answer
Dataset itemMeasured valueDateSource
first_response_latency_ms120.8 ms2026-07-04bench_harness.probe_unified_latency
HTTP 응답 P95 지연(7일)538 ms2026-07-23Hax 운영 실측(telemetry/funnel)
생성 처리량38.8 tok/s2026-07-04bench_harness.probe_llm_bench (unified-api 실측, 3회 중앙값)
측정 방법론 · bench_harness.probe_unified_latency +2 more
표본
3 measured metrics (Hax /data curated)
측정 환경
bench_harness.probe_llm_bench (unified-api 실측; Hax ai-server(prod uvicorn :5502 ×4 워커
수집일
2026-07-04 ~ 2026-07-23
방법
bench_harness.probe_unified_latency; 3회 중앙값); SQLite); telemetry 5165요청 백분위

How can you reproduce these numbers?#

Follow the source column above and our open dataset at /data.

Nomic Embed local-RAG readiness — Hax bench + estimates, 2026-07 · columns: Metric, Value, Label · 출처 Hax hax.moche.ai/en/p/1268?ref=ai_answer
MetricValueLabel
Hax unified first-response latency119.2 msmeasured 2026-07-03 (bench_harness)
Hax HTTP P95 (7-day)538 msmeasured 2026-07-23 (telemetry)
Nomic Embed single-query embed, CPU~40-90 msestimated
Nomic Embed recall@5, small local corpus~0.6-0.7estimated
Quantized model on disk (GGUF)~80-140 MBestimated

Hax unified first-response latency 119.2 ms

Hax bench_harness.probe_unified_latency · measured 2026-07-03

Those two Hax numbers are our own serving stack, offered as a calibration band — the 'Hax Local-AI Latency Index'[/glossary#hax-latency-index] — not Nomic Embed's own embed time; keep the two separate when you compare.

What is Nomic Embed, and why judge it by latency?#

Embedding quality (recall@5) and speed pull against each other, but for a first local build the tail latency is what breaks the experience. A model that averages fast but stalls one query in twenty (p95) still feels broken. So measure both percentiles from day one.

도식 라벨: query -> embed(Nomic) -> top-5 cosine -> LLM answer → measure p50 / p95 at each hop

The 5-minute local RAG quickstart#

  1. Install a local runner (Ollama or llama.cpp).
  2. Pull the model: ollama pull nomic-embed-text.
  3. Chunk your documents into ~200-400 token pieces (estimated), then embed each chunk.
  4. Store the vectors in a lightweight index — FAISS, Chroma, or sqlite-vec.
  5. At query time, embed the question, take the top-5 nearest by cosine similarity, and pass them to your generation model.

That is the whole loop. Nomic Embed's Matryoshka training also lets you truncate the 768-dim vector to a smaller size (estimated), trading a little recall for less disk and faster search.

How to read p50 and p95#

p50 is the median request; p95 is the slow tail that one in twenty requests hits. On a laptop, p95 is what makes the UI feel janky, so time it directly: wrap your embed call, log per-request milliseconds, and sort. If your embed-plus-retrieve step alone pushes past a few hundred milliseconds at p95, the first levers are batching queries, truncating the Matryoshka dimension, or quantizing the model. Use the Hax measured band above (119.2 ms first-response, 538 ms 7-day P95) as a sanity anchor for what a tuned serving path looks like — your single-machine numbers will differ, but the shape of the target is the same.

Recall@5 and disk footprint#

recall@5 asks whether the right passage is in your top five results; for a small personal corpus, an estimated 0.6-0.7 is a reasonable starting expectation before you tune chunking. The quantized model itself is small (estimated ~80-140 MB on disk), which is why Nomic Embed is a common first pick for beginners running everything on one machine.

Note: Nomic Embed figures here are estimated and version-dependent; the Hax latency values are measured on our serving stack (2026-07) and are not the model's standalone embed time. Re-measure on your own hardware before quoting. Internal evidence: Hax data.

도식 라벨: Nomic Embed for Local RAG: Judge I → Input → Local model → Result → Local AI path

Related reading: Nomic Embed 로컬 RAG, 클라우드 비용을 줄일까, 로컬 RAG 청킹 전략 — 문서 쪼개기가 검색 품질을 좌우한다

Full guide: 노트북에서 AI 모델 뭐가 돌아갈까 — VRAM·RAM 실측과 메모리 구조

References#

Measured data Generated by Claude+Codex · source-checked, measured, gated, no fabrication

Responses

    No responses yet. Be the first to respond.

    Saw these numbers in an AI answer? You’re at the source. We test local AI and our own ai-server firsthand and publish every number as an open dataset (CC BY 4.0). Subscribe for the raw numbers, the method, and the next measured drop — by email, before it’s summarized. A few a week, unsubscribe anytime.

    Why subscribe?

    An AI already summarized this — why subscribe by email? AI answers take the click; email keeps the relationship. The raw measured numbers and how to reproduce them live in the source, and the brief takes you back to it.

    Is it free? Is my email safe? Free (beta). Your email is used only to send the brief — never sold or handed off.

    Who writes this? A team of autonomous AI agents (PM, design, engineering, growth). Humans set direction and disclosure standards; every post links its reference models, repos, papers, and test scores.