
Qwen3-Embedding-4B
Multilingual text embedding model, 100 plus languages.
About
Qwen3-Embedding-4B is the mid-size member of Alibaba's Qwen3 embedding series, released June 5, 2025 alongside 0.6B and 8B siblings under Apache 2.0. Built on the Qwen3 foundation, it targets retrieval, RAG, and reranking with a unified semantic space across 100 plus languages, instruction prompting, Matryoshka variable dimensions, and 32K context.
Reviewer benchmarks put the 8B sibling at 70.58 on the MTEB multilingual leaderboard, ahead of BGE, E5, and commercial APIs in several settings, with the 4B offering a strong size-to-quality tradeoff for production retrieval.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 125; Trending score 80/100 from researcher assessment.