NEWVectors or files. Pick a path.Start →
    Models/Reranking/Qwen/Qwen3-VL-Reranker-8B
    HFRerankingapache-2.0

    Qwen3-VL-Reranker-8B

    by Qwen

    8B cross-encoder reranker for text, image, screenshot, and video retrieval

    91Kdl/month
    157likes
    8.8Bparams
    Identifiers
    Model ID
    Qwen/Qwen3-VL-Reranker-8B
    Feature URI
    mixpeek://reranker@v1/qwen3_vl_reranker_8b_v1

    Overview

    Qwen3-VL-Reranker-8B is the larger sibling of the 2B variant, built on the Qwen3-VL-8B-Instruct vision-language backbone. As a cross-encoder, it jointly attends to query and document tokens with full cross-attention, producing a single relevance score per pair. It handles text, images, screenshots, and video frames in both query and document positions, supporting 30+ languages and inputs up to 32K tokens.

    The 8B variant consistently outperforms the 2B model across most multimodal reranking benchmarks, making it the best choice when precision matters more than latency. On Mixpeek, it serves as a second-stage reranker that rescores candidates retrieved by a fast bi-encoder embedding model, dramatically improving top-K precision for cross-modal search.

    Architecture

    Cross-encoder architecture built on Qwen3-VL-8B-Instruct. Jointly processes query and document tokens with full bidirectional cross-attention. Outputs a scalar relevance score per pair. Supports text, images, screenshots, and video frames as both query and document inputs. 32K token context window. 30+ language support.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    
    // Managed: create a collection over a bucket; Mixpeek runs this model's extractor
    const collection = await mx.collections.create({
      namespace_id: "my-namespace",
      collection_name: "my-collection",
      source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
      feature_extractor: {
        feature_extractor_name: "feature_search",
        version: "v1",
        parameters: { model_id: "Qwen/Qwen3-VL-Embedding-8B" },
      },
    });

    Capabilities

    • Cross-modal reranking across text, image, screenshot, and video
    • Full cross-attention for higher precision than bi-encoder models
    • 32K token context for long-document reranking
    • 30+ language support including CJK
    • Consistently outperforms 2B variant on most benchmarks

    Use Cases on Mixpeek

    Two-stage multimodal retrieval: fast embedding search followed by high-precision reranking
    Visual document search: rerank candidate PDF pages by cross-attending to query and page screenshot
    Video scene reranking: rescore candidate scenes by cross-modal relevance to text queries

    Benchmarks

    DatasetMetricScoreSource
    Multimodal reranking (MMEB-V2)nDCG@10Best in class (8B)Qwen, 2026: arxiv,2601.04720
    Visual document rerankingnDCG@10Outperforms 2B variantQwen, 2026: arxiv,2601.04720

    Performance

    Input SizeUp to 32K tokens (query + document, text/image/video)
    GPU Latency~55ms / pair (A100)
    GPU Throughput~18 pairs/sec (A100)
    GPU Memory~16 GB

    Specification

    FrameworkHF
    OrganizationQwen
    FeatureReranking
    OutputRelevance score per candidate
    Modalities
    RetrieverCross-Modal Reranker
    Parameters8.8B
    Licenseapache-2.0
    Downloads/mo91K
    Likes157

    Research Paper

    Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

    arxiv.org

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

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

    Run on your data