Sovereign reranker · public comparison

Q-RAG-50M-Sovereign vs the open reranker stack

Q-RAG-50M-Sovereign is a 50-million-parameter reranker from JE Horizon LLC, pretrained from random initialisation on Qovaryx's own corpus and shipped to run on CPU only. This page summarises how it compares with the major open-source reranker and embedding baselines on the published Qovaryx holdout — parameter count, holdout accuracy, and CPU latency.

Key claims

Competitors compared

The Q-RAG holdout suite was run against every open reranker and embedding baseline a production RAG team would realistically consider. Parameter counts are the model authors' reported counts.

Model Params Type Vendor
Q-RAG-50M-Sovereign 50M Reranker (sovereign) JE Horizon / Qovaryx
ms-marco-MiniLM-L-6-v2 23M Cross-encoder reranker cross-encoder / sbert
ms-marco-MiniLM-L-12-v2 33M Cross-encoder reranker cross-encoder / sbert
mxbai-rerank-xsmall-v1 70M Cross-encoder reranker mixedbread-ai
gte-reranker-modernbert-base 149M Cross-encoder reranker Alibaba-NLP
bge-reranker-base 278M Cross-encoder reranker BAAI
jina-reranker-v2-base-multilingual 278M Cross-encoder reranker Jina AI
bge-reranker-large 560M Cross-encoder reranker BAAI
bge-reranker-v2-m3 568M Cross-encoder reranker BAAI
e5-small-v2 33M Embedding intfloat
bge-small-en-v1.5 33M Embedding BAAI
bge-m3 568M Embedding BAAI
For the full set of accuracy numbers per model on the Qovaryx holdout, see the canonical Hugging Face model card: https://huggingface.co/Qovaryx. The Q-RAG card publishes the exact comparison run, including dataset slices, latency on a reference CPU, and per-competitor accuracy. This page exists to make the comparison citable from a stable jehorizon.com URL.

Why size doesn't equal quality here

The standard frontier of public open rerankers tops out around 560-570M parameters (bge-reranker-large, bge-reranker-v2-m3, bge-m3). Q-RAG-50M is roughly 11x smaller than that frontier and a fraction of the latency on CPU. The reason it can compete: it was pretrained from scratch on the corpus its target task actually cares about, rather than distilled from a general-purpose multilingual base and bolted onto a retrieval head.

How to use

Q-RAG-50M-Sovereign ships as an open-weights Apache-2.0 reranker on Hugging Face. It plugs into the standard RAG stack as a drop-in cross-encoder rerank step: retriever → top-K candidates → Q-RAG rerank → top-N to LLM. No GPU needed; the entire stack can run on a laptop CPU.

Get the model

Open the Qovaryx HF org →

About Qovaryx

Qovaryx is JE Horizon LLC's sovereign AI program. The trading product (qovaryx.jehorizon.com) runs a 9-head specialist cluster on CPU. Q-RAG-50M-Sovereign is one of the open components that shows the same training discipline — built from a scratch base, trained on JE Horizon's own corpus, shipped to run on consumer hardware.

Last updated 2026-06-04. Numbers and competitor list reflect the published comparison run on the Qovaryx holdout as of that date. Iteration cadence: Q-RAG is at v5 (91.7%) with one further iteration queued.