LLM EU
Menu
Models

Qwen3 VL Embedding 2B

Alibaba Qwen

Catalogue only Open weights

Last reviewed:

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

Qwen3 VL Embedding 2B is published by Alibaba Qwen as open weights with an unpublished parameter count under Apache-2.0. The repository was created in January 2026 and is mirrored on Hugging Face. It turns text into vectors for retrieval instead of generating answers. The checkpoint is instruction-tuned and ships a chat template. The published configuration records no context window, so this card carries none. The card is catalogue-only: LLM EU does not run this model. The publisher states no language coverage on the model page.

Specifications

Provider
Alibaba Qwen (CN)
Context window
Not verified: the provider has not documented this claim.
Parameters
Not verified: the provider has not documented this claim.
Modalities
text, embedding
License
apache-2.0 · licence
Open weights
yes
Release date
07 Jan 2026
Tasks
Retrieval (RAG), Vision, Low cost

Languages

Strong: —

Adequate: —

Strong

    Adequate

      Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

      When to use it

      Strengths

      • open weights are published on Hugging Face and can be downloaded without a vendor agreement
      • Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
      • instruction-tuned checkpoint with a chat template in the repository
      • produces embeddings that a European operator can run next to its own vector store

      Limits

      • catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
      • no evaluation has been run by LLM EU
      • the published configuration records no context window, so the card carries none
      • the publisher states no parameter count in the harvested record
      • the hardware footprint cannot be estimated because no parameter count is published