Models / Qwen / Qwen3 VL Embedding 8B

Qwen3 VL Embedding 8B

JSON →
multimodal

A multimodal embedding model from the Qwen family, capable of processing both text and images for cross-modal retrieval and similarity.

textimagevisionfine-tunableopen-weights
Specs
Context & limits
context window
max output
Lifecycle
Dates
released2025-02-01
Resources