NEWVector Store Object Storage — 50x cheaper.Read the post →
    Models/Embeddings/Qwen/Qwen3-Embedding-0.6B
    HFText EmbeddingsApache 2.0

    Qwen3-Embedding-0.6B

    by Qwen

    Compact multilingual text embedding with 100+ language support

    2.1Mdl/month
    0.6Bparams
    Identifiers
    Model ID
    Qwen/Qwen3-Embedding-0.6B
    Feature URI
    mixpeek://text_extractor@v1/qwen3_embedding_06b_v1

    Overview

    Qwen3-Embedding-0.6B is the smallest model in the Qwen3 Embedding family, delivering surprisingly strong text embedding performance from just 600 million parameters. It supports 100+ languages, context lengths up to 32K tokens, and flexible embedding dimensions from 32 to 1024 via Matryoshka training.

    On Mixpeek, Qwen3-Embedding-0.6B is the ideal choice for high-throughput multilingual text indexing where you need fast embedding generation across diverse languages without sacrificing too much quality. It is particularly effective for indexing transcripts, captions, and extracted text.

    Architecture

    Dense transformer built on the Qwen3 0.6B foundation model, trained with a three-stage pipeline: large-scale unsupervised pre-training for foundational semantic understanding, supervised fine-tuning on high-quality labeled datasets, and model merging for optimal generalization. Supports instruction-aware embedding with task prefixes.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    await mx.collections.ingest({
    collection_id: "my-collection",
    source: { url: "https://example.com/document.pdf" },
    feature_extractors: [{
    name: "text_embedding",
    version: "v1",
    params: {
    model_id: "Qwen/Qwen3-Embedding-0.6B"
    }
    }]
    });

    Capabilities

    • 100+ language support with strong multilingual transfer
    • Flexible embedding dimensions from 32 to 1024
    • 32K token context window
    • Instruction-aware embedding for task-specific optimization
    • Compact 0.6B parameter footprint

    Use Cases on Mixpeek

    High-throughput multilingual text indexing for transcripts and captions
    Edge deployment for text search with minimal compute requirements
    Real-time semantic search where sub-5ms latency is critical

    Benchmarks

    DatasetMetricScoreSource
    MTEB MultilingualAvg Score64.33Qwen3-Embedding paper, June 2025
    MTEB RetrievalnDCG@10Competitive with BGE-M3Qwen3-Embedding paper, June 2025

    Performance

    Input Size32K tokens max
    Embedding Dim1024 (Matryoshka: 32-1024)
    GPU Latency~1.5ms / passage (A100)
    CPU Latency~12ms / passage
    GPU Throughput~660 passages/sec (A100)
    GPU Memory~1.2 GB

    0.6B params — smallest Qwen3 embedding model, ideal for high-throughput indexing

    Specification

    FrameworkHF
    OrganizationQwen
    FeatureText Embeddings
    Output1024-dim vector
    Modalitiesdocument, audio
    RetrieverText Similarity
    Parameters0.6B
    LicenseApache 2.0
    Downloads/mo2.1M

    Research Paper

    Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

    arxiv.org

    Build a pipeline with Qwen3-Embedding-0.6B

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

    Open Studio