Qwen/Qwen3-Embedding-4B
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 contextDense
View on Hugging Face → Fine-tuned from Qwen/Qwen3-4B-Base
Overview
Hardware: — drives latency, throughput & cost
| Size | 4.0B params |
|---|---|
| Tasks | /encode |
| License | apache-2.0 |
| Latency | 464 ms |
| Throughput | 5.7K tok/s |
| Cost | $0.039 /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: 2,560 |
| Max sequence length | 32,768 |
| Inputs | text |
Benchmarks
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.1447
map at 10 0.1137
mrr at 10 0.0335
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.4103
map at 10 0.1578
mrr at 10 0.6207
Performance L4 b1 c16
Corpus 6.1K tok/s
Corpus p50 553.1ms
Query 333 tok/s
Query p50 150.1ms
NanoFiQA2018Retrieval
Smaller subset of the FiQA financial QA dataset
Quality
ndcg at 10 0.6875
map at 10 0.6152
mrr at 10 0.7569
Performance L4 b1 c16
Corpus 5.2K tok/s
Corpus p50 375.9ms
Query 716 tok/s
Query p50 153.7ms
Compare (0)Compare →