Qwen 3 VL Embedding 2B
Qwen develops the Qwen 3 VL Embedding 2B, an open-source embedding model that excels at generating high-dimensional vectors for multimodal information retrieval and cross-modal understanding tasks. It is particularly adept at handling diverse inputs, including text, images, and videos, and producing semantically rich vectors that facilitate efficient similarity computation and retrieval.
Input
Output
Context
32K
Max Output
-
Parameters
2B
Technical Specifications
Model TypeEmbedding
Context Window32,000 tokens
Max Output TokensNot available
Parameters2B
Release DateJan 7, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Embedding
Capabilities
Resources & Links
Estimated GPU Requirements for Qwen 3 VL Embedding 2B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.