Als Markdown anzeigen

Qwen3-VL-Embedding

Qwen3-VL-Embedding is Qwen's embedding model built on Qwen3-VL. It maps images and text into one vector space, so a text query can find the page or photo it describes. LibreYOLO runs the 2B size on the embed task, the first VLM-based embedder in the library.

Aufgaben
embeddings
Größen
2b at 1024 px
Installation
pip install "libreyolo[vlm]"
Supportstufe
Geschwisterstufe, seit v1.8.0. Eine separate Produktoberfläche mit eigener Factory und eigenem Vertrag.
Upstream
Qwen3-VL-Embedding von Alibaba (Qwen Team), Apache-2.0. Publikation, Quelle
Lizenzen
Code Apache-2.0, Gewichte Apache-2.0. Kommerzielle Nutzung

Install

Qwen3-VL-Embedding belongs to LibreYOLO's VLM tier and needs the vlm extra.

bash
pip install "libreyolo[vlm]"

Predict

Weights download on first use from LibreYOLO/LibreQwen3VLEmbedding2b, a mirror of Qwen/Qwen3-VL-Embedding-2B with unchanged parameters. The architecture runs through the transformers Qwen3-VL implementation.

Python
from libreyolo import LibreVLM, SAMPLE_IMAGE model = LibreVLM("qwen3-vl-embedding-2b")   # weights download on first useresult = model.predict(SAMPLE_IMAGE)print(result.embeddings.shape)              # (1, 2048), unit length
Retrieval
from libreyolo import LibreVLM model = LibreVLM("qwen3-vl-embedding-2b")pages = model.embed("pages/")               # (N, 2048), one row per image # Queries carry a task instruction; images keep the default one.q = model.embed_text(    ["total due on the invoice"],    prompt="Retrieve images or text relevant to the user's query.",)                                           # (1, 2048)scores = q @ pages.T                        # cosine similarity

The family loads through LibreVLM(), or the LibreQwen3VLEmbedding class. It follows the same embed contract as CLIP, SigLIP2 and PE: predict(image) returns Results.embeddings of shape (1, 2048), embed(source) stacks one row per image, and embed_text(texts, prompt=None) returns text rows in the same space. Rows are L2-normalized, so a dot product is a cosine similarity.

Each input is a chat: a system instruction, then the image or the text. The hidden state at the last token, normalized, is the vector. prompt is that instruction. The default is upstream's "Represent the user's input."; set prompt= at construction to change it for images and texts, or pass it to embed_text per call. For retrieval, give queries a task instruction and keep the default for documents.

Images are resized on a 32-pixel grid to between 4,096 and 1,843,200 pixels, matching upstream's reference embedder. Against that embedder, in float32 on CPU, text vectors differ by at most 7.4e-7 and image vectors have a cosine of at least 0.99998.

Variants

One size, 2b. The 8B size is not wrapped. Not supported: combined image-plus-text inputs, video clips (a video is embedded frame by frame), and Matryoshka truncation as an option; slice the first k columns and re-normalize instead.

Export

Inference only: chat(), set_classes(), train(), val() and export() raise.

Licensing

Prüfe die Lizenz im Hugging-Face-Repository der konkreten Gewichte, die du herunterlädst. Jeder Checkpoint in der LibreYOLO-Organisation hat eine Lizenz, und sie ist innerhalb einer Familie nicht immer gleich. Dieses Repository ist die maßgebliche Quelle. Die Zusammenfassung unten beschreibt den Stand bei der letzten Verifizierung dieser Seite.

Dies ist eine Beschreibung der beteiligten Lizenzen und keine Rechtsberatung. Wenn die Antwort kommerziell relevant ist, lies die Lizenzen selbst und hole eigenen Rechtsrat ein.

Originalarbeit
Qwen3-VL-Embedding, Alibaba (Qwen Team)
Upstream-Lizenz
Apache-2.0
LibreYOLO-Code
MIT
Gewichte
Apache-2.0, erneut unter huggingface.co/LibreYOLO veröffentlicht
Einordnung
Apache-2.0 is a permissive license, so the Qwen3-VL-Embedding-2B weights can be used in commercial and closed-source products. Redistributing them means keeping the license text and attribution notices, and the license grants a patent license. LibreYOLO copies no model source: the Qwen3-VL architecture runs through the Apache-2.0 Hugging Face Transformers implementation, and libreyolo/models/vlm/qwen3vl_embedding.py (MIT) adapts only the input conventions and last-token pooling of the reference embedder in QwenLM/Qwen3-VL-Embedding at commit 393e2978d27852b0d0230d6994f37f9c15bed73c (Apache-2.0, see libreyolo/models/vlm/NOTICE). The weights are a mirrored snapshot of Qwen/Qwen3-VL-Embedding-2B at revision 9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda, hosted at LibreYOLO/LibreQwen3VLEmbedding2b with learned parameters unchanged and not gated; the upstream Hugging Face repository ships no LICENSE file, so the mirror carries the Apache-2.0 text from the GitHub repository.

Qwen3-VL-Embedding-2B is Apache-2.0, by the Qwen team at Alibaba. Commercial use is allowed. The mirror is not gated; because the upstream Hugging Face repository ships no LICENSE file, it carries the Apache-2.0 text from the GitHub repository.

Citation

@article{qwen3vlembedding,
  title={Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking},
  author={Li, Mingxin and Zhang, Yanzhao and Long, Dingkun and Chen, Keqin and Song, Sibo and Bai, Shuai and Yang, Zhibo and Xie, Pengjun and Yang, An and Liu, Dayiheng and Zhou, Jingren and Lin, Junyang},
  journal={arXiv},
  year={2026}
}

Aus dem Zitierblock der Autoren unter github.com/QwenLM/Qwen3-VL-Embedding#citation kopiert.

Mit LibreYOLO v1.8.0 verifiziert. Supporttabellen, Checkpoints und Benchmarkwerte auf dieser Seite werden aus der veröffentlichten Bibliothek und den publizierten Gewichten generiert und nicht von Hand geschrieben.