Back to Models
EmbeddingCheck exact model cardOpen weights where released

Qwen3 Embedding

Alibaba Qwen · Qwen

Qwen embedding model family worth testing for modern RAG and multilingual retrieval stacks.

Best for

Builders who want a newer embedding family to compare against E5, BGE, and Jina.

Tradeoffs

Pick the exact size and release based on latency, language coverage, and retrieval benchmarks.

Local hardware notes

Smaller embedding variants are practical for local RAG prototypes.

Local workflow notes

Smaller embedding variants are practical for local RAG and retrieval experiments.

Local runtimes: Sentence Transformers, Transformers

Platforms: Windows, macOS, Linux

HardwareCPU or small GPURuntimeSentence Transformers, TransformersContextCheck current model cardUpdated2026
Qwen on Hugging Face →