Yz

qwen3-embedding

Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes

Embedding 0.6b 4b 8b
Hızlı Kurulum (Ollama kuruluysa) 
ollama run qwen3-embedding

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 4.7GB 40K Text ollama run qwen3-embedding:latest
0.6b 639MB 32K Text ollama run qwen3-embedding:0.6b
4b 2.5GB 40K Text ollama run qwen3-embedding:4b
8b 4.7GB 40K Text ollama run qwen3-embedding:8b
0.6b-q8_0 639MB 32K Text ollama run qwen3-embedding:0.6b-q8_0
0.6b-fp16 1.2GB 32K Text ollama run qwen3-embedding:0.6b-fp16
4b-q4_K_M 2.5GB 40K Text ollama run qwen3-embedding:4b-q4_K_M
4b-q8_0 4.3GB 40K Text ollama run qwen3-embedding:4b-q8_0
4b-fp16 8.0GB 40K Text ollama run qwen3-embedding:4b-fp16
8b-q4_K_M 4.7GB 40K Text ollama run qwen3-embedding:8b-q4_K_M
8b-q8_0 8.0GB 40K Text ollama run qwen3-embedding:8b-q8_0
8b-fp16 15GB 40K Text ollama run qwen3-embedding:8b-fp16

Model Detayları ve Benchmarklar (kaynak: ollama.com)

Highlights

The Qwen3 Embedding model series is specifically designed for text embedding tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

Exceptional Versatility: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58).

Comprehensive Flexibility: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for embedding models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, these models allow for flexible vector definitions across all dimensions, support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.

Multilingual Capability: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.

Qwen3-Embedding-8B has the following features:

  • Model Type: Text Embedding
  • Supported Languages: 100+ Languages
  • Number of Paramaters: 8B
  • Context Length: 32k
  • Embedding Dimension: Up to 4096, supports user-defined output dimensions ranging from 32 to 4096

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to the model’s blog, GitHub.