[Models](/models)/[Reranking](/models?category=reranking)/Qwen/Qwen3-Reranker-8B

HFRerankingApache 2.0

# Qwen3-Reranker-8B

by Qwen

SOTA text cross-encoder reranker: instruction-aware, 100+ languages

1.8Mdl/month

8Bparams

[HuggingFace](https://huggingface.co/Qwen/Qwen3-Reranker-8B)[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

`Qwen/Qwen3-Reranker-8B`

## Deploy Qwen3-Reranker-8B

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

Qwen3-Reranker-8B is the text reranking counterpart to Qwen3-Embedding, currently the top-scoring model on MTEB-R reranking benchmarks (69.76). It operates as a cross-encoder: concatenating query and document into a single input and running full bidirectional attention to produce a relevance score.

Like the embedding model, it supports instruction-tuned task conditioning: you can specify what makes a document relevant for your specific use case. On Mixpeek, it slots into the second stage of a two-stage retrieval pipeline: the embedding model retrieves candidates, and the reranker precision-sorts the top results.

## Architecture

Cross-encoder architecture on Qwen3 8B backbone. Processes concatenated query-document pairs with full bidirectional attention. Outputs a scalar relevance score. Supports instruction prefixes for task-specific ranking criteria.

## 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 Qwen3-Reranker-8B 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

*   Full bidirectional cross-attention between query and document
*   Instruction-tuned for task-specific relevance criteria
*   100+ language support
*   32K context window for reranking long documents
*   #1 on MTEB-R reranking benchmark (69.76)

## Use Cases on Mixpeek

Second-stage reranking in RAG pipelines for precision improvement

Multilingual document reranking for cross-language search

Long-document relevance scoring without chunking

Instruction-conditioned ranking for domain-specific retrieval

## Benchmarks

Dataset

Metric

Score

Source

MTEB-R (overall)

Score

69.76

Qwen, 2026: MTEB Leaderboard

## Performance

Input SizeUp to 32K tokens (query + document)

GPU Latency~85ms / pair (A100)

GPU Throughput~12 pairs/sec (A100)

GPU Memory~16 GB

## Common Pipeline Companions

[

Qwen/Qwen3-Embedding-8B

First-stage embedding retrieval

](/model/Qwen/Qwen3-Embedding-8B)[

Qwen/Qwen3-VL-Embedding-8B

Multimodal first-stage retrieval

](/model/Qwen/Qwen3-VL-Embedding-8B)

## 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

OrganizationQwen

FeatureReranking

OutputRelevance score per candidate

Modalities

RetrieverCross-Modal Reranker

Parameters8B

LicenseApache 2.0

Downloads/mo1.8M

[

### Research Paper

Qwen3-Embedding: Advancing Text and Multimodal Retrieval

arxiv.org](https://arxiv.org/abs/2601.04720)

### Build a pipeline with Qwen3-Reranker-8B

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)