← Catalog
Qwen/Qwen3-Embedding-0.6B Add to compare Open comparison →
Primitive: /encode · Encode ·
Qwen3
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).
Long context Dense
View on Hugging Face → Fine-tuned from Qwen/Qwen3-0.6B-Base
Overview
Hardware:
L4 RTX-PRO-6000 — drives latency, throughput & cost
Size 596M params Tasks /encode License apache-2.0 Latency 157 ms Throughput 20.6K tok/s Cost $0.011 /1M tok
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Embedding Output types Dense Dimensions dense: 1,024 Max sequence length 32,768 Inputs text
Benchmarks Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Quality
map at 10 0.4399
mrr at 10 0.4949
ndcg at 10 0.5034
Performance L4 b1 c16
Corpus 21.2K tok/s
Corpus p50 94.7ms
Query 2.7K tok/s
Query p50 58.2ms
Reference →
Code search with natural language queries
Corpus: 6,267 Queries: 500
Quality
map at 10 0.3120
mrr at 10 0.3694
ndcg at 10 0.3977
Performance L4 b1 c16
Corpus 12.7K tok/s
Corpus p50 66.3ms
Query 1.4K tok/s
Query p50 58.7ms
Reference →
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
map at 10 0.3849
mrr at 10 0.5510
ndcg at 10 0.4727
Performance L4 b1 c16
Corpus 20.8K tok/s
Corpus p50 128.2ms
Query 3.1K tok/s
Query p50 55.5ms
Reference →
Question answering on consumer contracts
Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus 19.9K tok/s
Corpus p50 439.6ms
Query 4.1K tok/s
Query p50 59.0ms
Reference →
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3689
map at 10 0.1395
mrr at 10 0.5716
Performance L4 b1 c16
Corpus 21.2K tok/s
Corpus p50 240.7ms
Query 1.3K tok/s
Query p50 55.9ms
Reference →
Smaller subset of the FiQA financial QA dataset
Quality
ndcg at 10 0.6538
map at 10 0.5819
mrr at 10 0.7257
Performance L4 b1 c16
Corpus 18.5K tok/s
Corpus p50 144.8ms
Query 1.8K tok/s
Query p50 78.3ms
Reference →
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
map at 10 0.1474
mrr at 10 0.4079
ndcg at 10 0.2440
Performance L4 b1 c16
Corpus 20.0K tok/s
Corpus p50 156.9ms
Query 3.0K tok/s
Query p50 54.5ms
Reference →
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
map at 10 0.6456
mrr at 10 0.6556
ndcg at 10 0.6945
Performance L4 b1 c16
Corpus 21.1K tok/s
Corpus p50 218.8ms
Query 3.7K tok/s
Query p50 61.3ms
Reference →
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Quality
map at 10 0.8711
mrr at 10 0.8711
ndcg at 10 0.8902
Performance L4 b1 c16
Corpus 20.6K tok/s
Corpus p50 172.8ms
Query 18.9K tok/s
Query p50 239.7ms
Reference →
