Qwen3 VL Embedding 8B

提供商Qwen
分类sentence-similarity
许可证apache-2.0
下载量689.6K
星标65

简介

Qwen3 VL Embedding 8B 是阿里巴巴通义千问团队推出的多模态向量模型。与传统的纯文本 Embedding 不同，它能将图像和文本统一映射到同一个向量空间，实现真正的“图文互检索”。对于开发者而言，这意味着你可以用它构建更精准的视觉 RAG（检索增强生成）系统，或者在海量图片库中通过自然语言进行语义搜索。该模型基于 8B 参数规模，在保持强大表征能力的同时，部署门槛相对较低，是替代传统 CLIP 类模型、提升多模态检索精度的高质量选择。

核心亮点

  • 支持图文统一向量化，实现高效语义互检索
  • 大幅增强视觉 RAG 系统的知识检索精度
  • 8B 参数规模，在性能与部署成本间取得平衡
  • Apache-2.0 协议，对商业应用极其友好

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Qwen/Qwen3-VL-Embedding-8B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-VL-Embedding-8B")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download Qwen/Qwen3-VL-Embedding-8B

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download Qwen/Qwen3-VL-Embedding-8B config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-VL-Embedding-8B')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Qwen/Qwen3-VL-Embedding-8B')
tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-VL-Embedding-8B')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model Qwen/Qwen3-VL-Embedding-8B

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model Qwen/Qwen3-VL-Embedding-8B README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-VL-Embedding-8B')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/Qwen/Qwen3-VL-Embedding-8B.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Qwen/Qwen3-VL-Embedding-8B.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'Qwen/Qwen3-VL-Embedding-8B')

完整文档

来源: HuggingFace

---
license: apache-2.0
library_name: sentence-transformers
pipeline_tag: sentence-similarity

base_model:

  • Qwen/Qwen3-VL-8B-Instruct

tags:
  • sentence-transformers

  • transformers

  • multimodal embedding

  • qwen

  • embedding

---

Qwen3-VL-Embedding-8B

<p align="center">
<img src="https://model-demo.oss-cn-hangzhou.aliyuncs.com/Qwen3-VL-Embedding.png" width="400"/>
<p>

Highlights

The Qwen3-VL-Embedding and Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities.

While the Embedding model generates high-dimensional vectors for broad applications like retrieval and clustering, the Reranker model is engineered to refine these results, establishing a comprehensive pipeline for state-of-the-art multimodal search.

  • Multimodal Versatility: Both models seamlessly handle a wide range of inputs—including text, images, screenshots, and video—within a unified framework. They deliver state-of-the-art performance across diverse multimodal tasks such as image-text retrieval, video-text matching, visual question answering (VQA), and multimodal content clustering.
  • Unified Representation Learning (Embedding): By leveraging the Qwen3-VL architecture, the Embedding model generates semantically rich vectors that capture both visual and textual information in a shared space. This facilitates efficient similarity computation and retrieval across different modalities.
  • High-Precision Reranking (Reranker): We also introduce the Qwen3-VL-Reranker series to complement the embedding model. The reranker takes a (query, document) pair as input—where both query and document may contain arbitrary single or mixed modalities—and outputs a precise relevance score. In retrieval pipelines, the two models are typically used in tandem: the embedding model performs efficient initial recall, while the reranker refines results in a subsequent re-ranking stage. This two-stage approach significantly boosts retrieval accuracy.
  • Exceptional Practicality: Inheriting Qwen3-VL’s multilingual capabilities, the series supports over 30 languages, making it ideal for global applications. It is highly practical for real-world scenarios, offering flexible vector dimensions, customizable instructions for specific use cases, and strong performance even with quantized embeddings. These capabilities enable developers to seamlessly integrate both models into existing pipelines, unlocking powerful cross-lingual and cross-modal understanding.

Model Overview

Qwen3-VL-Embedding-8B has the following features:

  • Model Type: MultiModal Embedding
  • Supported Languages: 30+ Languages
  • Supported Input Modalities: Text, images, screenshots, videos, and arbitrary multimodal combinations (e.g., text + image, text + video)
  • Number of Parameters: 8B
  • Context Length: 32k
  • Embedding Dimension: Up to 4096, supports user-defined output dimensions ranging from 64 to 4096

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our technical report, blog, GitHub.

Qwen3-VL-Embedding and Qwen3-VL-Reranker Model list

| Model | Size | Model Layers | Sequence Length | Embedding Dimension | Quantization Support | MRL Support | Instruction Aware |
|---|---|---|---|---|----------------------|---|---|
| Qwen3-VL-Embedding-2B | 2B | 28 | 32K | 2048 | Yes | Yes | Yes |
| Qwen3-VL-Embedding-8B | 8B | 36 | 32K | 4096 | Yes | Yes | Yes |
| Qwen3-VL-Reranker-2B | 2B | 28 | 32K | - | - | - | Yes |
| Qwen3-VL-Reranker-8B | 8B | 36 | 32K | - | - | - | Yes |

> Note:
> - Quantization Support indicates the supported quantization post process for the output embedding.
> - MRL Support indicates whether the embedding model supports custom dimensions for the final embedding.
> - Instruction Aware notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
> Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.

Model Performance

Evaluation Results on MMEB-V2

Results on the MMEB-V2 benchmark. All models except IFM-TTE have been re-evaluated on the updated VisDoc OOD split. CLS: classification, QA: question answering, RET: retrieval, GD: grounding, MRET: moment retrieval, VDR: ViDoRe, VR: VisRAG, OOD: out-of-distribution.

| Model | Model Size | Image CLS | Image QA | Image RET | Image GD | Image Overall | Video CLS | Video QA | Video RET | Video MRET | Video Overall | VisDoc VDRv1 | VisDoc VDRv2 | VisDoc VR | VisDoc OOD | VisDoc Overall | All |
|----------------------------|---------|-------|------|------|------|-----------|------|------|------|------|------|-------|------|--------|------|------|--------|
| # of Datasets → | | 10 | 10 | 12 | 4 | 36 | 5 | 5 | 5 | 3 | 18 | 10 | 4 | 6 | 4 | 24 | 78 |
| VLM2Vec | 2B | 58.7 | 49.3 | 65.0 | 72.9 | 59.7 | 33.4 | 30.5 | 20.6 | 30.7 | 28.6 | 49.8 | 13.5 | 51.8 | 48.2 | 44.0 | 47.7 |
| VLM2Vec-V2 | 2B | 62.9 | 56.3 | 69.5 | 77.3 | 64.9 | 39.3 | 34.3 | 28.8 | 36.8 | 34.6 | 75.5 | 44.9 | 79.4 | 62.2 | 69.2 | 59.2 |
| GME-2B | 2B | 54.4 | 29.9 | 66.9 | 55.5 | 51.9 | 34.9 | 42.0 | 25.6 | 31.1 | 33.6 | 86.1 | 54.0 | 82.5 | 67.5 | 76.8 | 55.3 |
| GME-7B | 7B | 57.7 | 34.7 | 71.2 | 59.3 | 56.0 | 37.4 | 50.4 | 28.4 | 37.0 | 38.4 | 89.4 | 55.6 | 85.0 | 68.3 | 79.3 | 59.1 |
| Ops-MM-embedding-v1 | 8B | 69.7 | 69.6 | 73.1 | 87.2 | 72.7 | 59.7 | 62.2 | 45.7 | 43.2 | 53.8 | 80.1 | 59.6 | 79.3 | 67.8 | 74.4 | 68.9 |
| IFM-TTE | 8B | 76.7 | 78.5 | 74.6 | 89.3 | 77.9 | 60.5 | 67.9 | 51.7 | 54.9 | 59.2 | 85.2 | 71.5 | 92.7 | 53.3 | 79.5 | 74.1 |
| RzenEmbed | 8B | 70.6 | 71.7 | 78.5 | 92.1 | 75.9 | 58.8 | 63.5 | 51.0 | 45.5 | 55.7 | 89.7 | 60.7 | 88.7 | 69.9 | 81.3 | 72.9 |
| Seed-1.6-embedding-1215 | unknown | 75.0 | 74.9 | 79.3 | 89.0 | 78.0 | 85.2 | 66.7 | 59.1 | 54.8 | 67.7 | 90.0 | 60.3 | 90.0 | 70.7 | 82.2 | 76.9 |
| Qwen3-VL-Embedding-2B | 2B | 70.2 | 74.4 | 74.9 | 88.6 | 75.0 | 72.8 | 63.8 | 52.3 | 51.6 | 61.1 | 85.2 | 66.0 | 86.3 | 74.3 | 80.2 | 73.4 |
| Qwen3-VL-Embedding-8B | 8B | 74.4 | 81.0 | 80.0 | 92.2 | 80.1 | 79.1 | 70.1 | 57.0 | 53.2 | 66.1 | 88.2 | 69.9 | 88.8 | 78.3 | 83.3 | 77.9 |

Evaluation Results on MMTEB

Results on the MMTEB benchmark.

| Model | Size | Mean (Task) | Mean (Type) | Bitxt Mining | Class. | Clust. | Inst. Retri. | Multi. Class. | Pair. Class. | Rerank | Retri. | STS |
|----------------------------------|:-------:|:-------------:|:-------------:|:--------------:|:--------:|:--------:|:--------------:|:---------------:|:------

查看官方来源