[Models](/models)/[Reranking](/models?category=reranking)/cross-encoder/ettin-reranker-1b-v1

HFRerankingApache-2.0

# ettin-reranker-1b-v1

by cross-encoder

State-of-the-art cross-encoder reranker matching its 1.5B teacher at 1B parameters

52Kdl/month

1Bparams

[HuggingFace](https://huggingface.co/cross-encoder/ettin-reranker-1b-v1)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`cross-encoder/ettin-reranker-1b-v1`

## Deploy ettin-reranker-1b-v1

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

Ettin Reranker 1B is the flagship model in the Ettin reranker family (17M to 1B parameters), trained via pointwise MSE distillation from the mxbai-rerank-large-v2 teacher. Built on Ettin ModernBERT encoders, it matches the teacher's MTEB Retrieval score within 0.0001 nDCG@10 while being smaller and faster.

The Ettin family provides a reranker at every size class, letting you trade latency for quality. The 150M variant runs under 10ms per query-document pair on GPU; the 1B variant delivers maximum accuracy for quality-critical retrieval.

## Architecture

ModernBERT encoder backbone (Ettin variant) with a cross-encoder classification head. Takes concatenated query-document input and outputs a relevance score. Trained via pointwise MSE distillation from mxbai-rerank-large-v2 on diverse retrieval datasets.

## Mixpeek SDK Integration

IngestRetrieve

// Reranking is a retriever STAGE in Mixpeek, not an ingest-time extractor.
// The rerank stage runs a cross-encoder inference service; the shipped default
// is BAAI/bge-reranker-v2-m3. Pointing it at ettin-reranker-1b-v1 means registering that
// model as a custom reranker plugin and naming it in feature\_uri, which is an
// Enterprise path. Stage contract read from GET /v1/discovery/stages.
const retriever = await mx.retrievers.create({
  namespace\_id: "my-namespace",
  retriever\_name: "search-then-rerank",
  stages: \[
    {
      stage\_name: "candidates",
      stage\_id: "feature\_search",
      parameters: { limit: 100 },
    },
    {
      stage\_name: "rerank\_results",
      stage\_id: "rerank",
      parameters: {
        inference\_name: "BAAI\_\_bge\_reranker\_v2\_m3",
        query: "{{INPUT.query}}",
        document\_field: "content",
        top\_k: 10,
      },
    },
  \],
});

## Capabilities

*   SOTA reranking at 1B parameters on MTEB Retrieval
*   Family of 6 sizes (17M-1B) for latency/quality tradeoffs
*   Matches 1.54B teacher within 0.0001 nDCG@10
*   Compatible with any first-stage retriever
*   Apache 2.0 license

## Use Cases on Mixpeek

Second-stage reranking in Mixpeek multi-stage retriever pipelines

Precision-critical document retrieval where recall is already high

Low-latency reranking with smaller family variants (150M, 400M)

## Benchmarks

Dataset

Metric

Score

Source

MTEB Retrieval (eng, v2)

nDCG@10

≈teacher (0.0001 gap)

Ettin blog, May 2026

NanoBEIR (13 datasets)

nDCG@10

SOTA at 1B

Ettin blog, May 2026

## Performance

Input SizeUp to 8192 tokens (query + document)

GPU Latency~18ms / pair (A100)

GPU Throughput~450 pairs/sec (A100, batch 32)

GPU Memory~2.1 GB

## Common Pipeline Companions

[

BAAI/bge-m3

First-stage dense retrieval before Ettin reranking

](/model/BAAI/bge-m3)[

nomic-ai/modernbert-embed-base

Lightweight first-stage retrieval

](/model/nomic-ai/modernbert-embed-base)

## Explore on Mixpeek

[

More Reranking models

Compare alternatives in this category

](/models?category=reranking)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkHF

Organizationcross-encoder

FeatureReranking

OutputRelevance score per candidate

Modalities

RetrieverCross-Modal Reranker

Parameters1B

LicenseApache-2.0

Downloads/mo52K

[

### Research Paper

Introducing the Ettin Reranker Family

arxiv.org](https://huggingface.co/blog/ettin-reranker)

### Build a pipeline with ettin-reranker-1b-v1

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

Qwen/Qwen3-VL-Reranker-2B

Reranking

](/model/Qwen/Qwen3-VL-Reranker-2B)[

Qwen/Qwen3-VL-Reranker-8B

Reranking

](/model/Qwen/Qwen3-VL-Reranker-8B)[

nvidia/llama-nemotron-rerank-1b-v2

Reranking

](/model/nvidia/llama-nemotron-rerank-1b-v2)[

nvidia/llama-nemotron-rerank-vl-1b-v2

Reranking

](/model/nvidia/llama-nemotron-rerank-vl-1b-v2)