Qwen3-VL-Embedding-8B

Home/Models/Qwen/Qwen3-VL-Embedding-8B

Qwen/Qwen3-VL-Embedding-8B

kind: original
quant: bf16 (16-bit)
family: qwen
modality: sentence-similarity
root model: Qwen/Qwen3-VL-8B-Instruct
provider: Qwen
license: apache-2.0
language: —
context: 32k
library: sentence-transformers
vRAM (GB): 8
size on disk: —
downloads: 2,193,134
likes: 463
created: —
last modified: 2026-04-16T08:55:18+00:00 (2026)
huggingface: https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B
tags: sentence-transformerssafetensorsqwen3_vlimage-text-to-texttransformersmultimodal embeddingqwenembeddingsentence-similarityarxiv:2601.04720base_model:Qwen/Qwen3-VL-8B-Instructbase_model:finetune:Qwen/Qwen3-VL-8B-Instructlicense:apache-2.0endpoints_compatibleregion:us

no scores extracted for this variant.

title	author	status	type
Integrate with Sentence Transformers v5.4	tomaarsen	merged	disc
GGUF Quantization	Znerual	open	disc
Comparison with Qwen3-Embedding-8B?	clapointe	open	disc
add model pipeline info and technical report info	thenlper	merged	disc
支持多图吗	chaxjli	open	disc
Add pipeline tag, library name, and paper link	nielsr	open	disc
Why isn't there an MoE version of the Qwen3-VL-Embedding model?	guobabert	open	disc
Add vLLM and SGLang usage examples	yuhao318	merged	disc
Update scripts/qwen3_vl_embedding.py	zyznull	merged	disc
Update README.md	thenlper	merged	disc
Update README.md	thenlper	closed	disc