NEWVectors or files. Pick a path.Start →
    Models/Reranking/nvidia/llama-nemotron-rerank-1b-v2
    HFRerankingother

    llama-nemotron-rerank-1b-v2

    by nvidia

    Lightweight 1B text reranker for production retrieval pipelines

    815Kdl/month
    61likes
    1.2Bparams
    Identifiers
    Model ID
    nvidia/llama-nemotron-rerank-1b-v2
    Feature URI
    mixpeek://reranker@v1/nvidia_nemotron_rerank_1b_v2

    Overview

    Llama-Nemotron Rerank 1B is NVIDIA's lightweight cross-encoder reranker based on Llama-3.2-1B. At 1B parameters, it is 3.5x smaller than mistral-based rerankers while delivering competitive quality across 26 languages and 8192-token context. It supports true/false relevance scoring: the model outputs the probability that a document is relevant to a query.

    On Mixpeek, this reranker slots into the second stage of retrieval pipelines: after a fast embedding-based first stage returns top-K candidates, the reranker rescores each candidate with full cross-attention between query and document, significantly improving precision.

    Architecture

    Cross-encoder based on Llama-3.2-1B. Outputs relevance probability via true/false token logits. 8192-token max context. 26-language support. Trained with progressive curriculum on diverse relevance data.

    Mixpeek SDK Integration

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

    • 1B parameters: 3.5x smaller than 4B rerankers
    • 26-language support including CJK and European languages
    • 8192-token context for long document reranking
    • Cross-lingual reranking (86.83% on MLQA)
    • Production-grade latency on modest hardware

    Use Cases on Mixpeek

    Two-stage retrieval: rerank embedding search results for higher precision
    Multilingual search: rerank across 26 languages with one model
    Long document reranking: handle full documents up to 8K tokens
    RAG pipelines: improve context quality before LLM generation

    Benchmarks

    DatasetMetricScoreSource
    NQ + HotpotQA + FiQA + TechQARecall@573.64%NVIDIA, 2026: Model Card
    MLQA (cross-lingual, 7 langs)Recall@586.83%NVIDIA, 2026: Model Card
    MLDR (long docs, 13 langs)Recall@570.69%NVIDIA, 2026: Model Card

    Performance

    Input SizeText (up to 8192 tokens)
    GPU Latency~5ms / pair (A100)
    GPU Throughput~200 pairs/sec (A100)
    GPU Memory~2.5 GB

    Specification

    FrameworkHF
    Organizationnvidia
    FeatureReranking
    OutputRelevance score per candidate
    Modalities
    RetrieverCross-Modal Reranker
    Parameters1.2B
    Licenseother
    Downloads/mo815K
    Likes61

    Research Paper

    NVIDIA NeMo Retriever Reranking

    arxiv.org

    Build a pipeline with llama-nemotron-rerank-1b-v2

    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