NEWWhy single embeddings fail for video.Read the post →
    Models/Embeddings/nomic-ai/nomic-embed-text-v2-moe
    HFText EmbeddingsApache-2.0

    nomic-embed-text-v2-moe

    by nomic-ai

    First Mixture-of-Experts text embedding model with 100-language multilingual support

    1.4Mdl/month
    475M total / 305M activeparams
    Identifiers
    Model ID
    nomic-ai/nomic-embed-text-v2-moe
    Feature URI
    mixpeek://text_extractor@v1/nomic_embed_v2_moe_v1

    Overview

    Nomic Embed Text v2 MoE is the first general-purpose Mixture-of-Experts text embedding model, using 8 experts with top-2 routing to deliver 475M total parameters but only 305M active at inference. Trained on 1.6B high-quality pairs with consistency filtering, it achieves state-of-the-art performance on both BEIR and MIRACL benchmarks while remaining competitive with models twice its size.

    On Mixpeek, nomic-embed-text-v2-moe provides efficient multilingual text embeddings for search pipelines that span ~100 languages, with Matryoshka dimension support (768 down to 256) for flexible storage and retrieval tradeoffs.

    Architecture

    Mixture-of-Experts transformer encoder with 8 experts, top-2 routing. 475M total parameters, 305M active during inference. Trained with weakly-supervised contrastive pretraining followed by supervised fine-tuning. Matryoshka representation learning for flexible output dimensions.

    Mixpeek SDK Integration

    from mixpeek import Mixpeek
    mx = Mixpeek(api_key="YOUR_KEY")
    mx.ingest(
    collection_id="multilingual-docs",
    source="s3://documents/",
    extractors=[{
    "type": "text_embedding",
    "model": "nomic-ai/nomic-embed-text-v2-moe",
    "output_feature": "text_embedding"
    }]
    )

    Capabilities

    • MoE efficiency: 305M active / 475M total parameters
    • ~100 language multilingual support
    • 768-dimensional embeddings with Matryoshka truncation to 256
    • State-of-the-art on BEIR and MIRACL benchmarks
    • Apache 2.0 fully open-source

    Use Cases on Mixpeek

    Multilingual document search across global content libraries
    Cost-efficient text retrieval where MoE reduces compute per query
    Hybrid search pipelines with flexible dimension tradeoffs via Matryoshka

    Benchmarks

    DatasetMetricScoreSource
    BEIRnDCG@1052.86Nomic AI, 2025 — nomic-embed-text-v2 paper
    MIRACLnDCG@1065.80Nomic AI, 2025 — nomic-embed-text-v2 paper

    Performance

    Input Size8192 tokens
    Embedding Dim768 (Matryoshka: 256-768)
    GPU Latency~4ms / query (A100)
    GPU Throughput~1500 queries/sec (A100, batch 64)
    GPU Memory~1.9 GB

    Specification

    FrameworkHF
    Organizationnomic-ai
    FeatureText Embeddings
    Output1024-dim vector
    Modalitiesdocument, audio
    RetrieverText Similarity
    Parameters475M total / 305M active
    LicenseApache-2.0
    Downloads/mo1.4M

    Research Paper

    Training Sparse Mixture Of Experts Text Embedding Models

    arxiv.org

    Build a pipeline with nomic-embed-text-v2-moe

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

    Open Studio