← BACK TO AI LAB

AI LAB / RAG / Local AI

RAG Retrieval on Local Models

Comparing retrieval quality and latency across compact local embedding models.

RAGLocal AIBenchmarks
EXPERIMENT
EXP-014
STATUS
complete
DATE
Aug 26, 2026
TAGS
RAG · Local AI · Benchmarks

EXPERIMENT / HYPOTHESIS

A compact local embedding model can retain at least 90% recall while avoiding external inference latency.

  1. 01Build a 500-query dataset across six document domains
  2. 02Index identical chunks with three embedding models
  3. 03Measure recall@5, MRR, indexing time, and query latency
Recall@5
91.4%
P95 latency
312ms
Queries
500

CONCLUSIONThe best compact model cleared the recall threshold and was faster for private, interactive workloads, but struggled more with jargon-heavy queries.

01

Setup

Every model received the same normalized chunks and queries. Results were evaluated against human-labeled relevant passages.

  • Fixed chunking
  • Warm and cold latency
  • Domain-level slices
02

Result

Local retrieval was competitive for general queries. Hosted embeddings still led on specialized terminology, suggesting a workload-aware routing policy.

  • Strong general recall
  • Predictable privacy
  • Domain-specific quality gap