← Catalog
Alibaba-NLP/gte-Qwen2-1.5B-instruct Add to compare Open comparison →
Primitive: /encode · Encode ·
Qwen2
gte-Qwen2-1.5B-instruct is the latest model in the gte (General Text Embedding) model family. The model is built on Qwen2-1.5B LLM model and use the same training data and strategies as the gte-Qwen2-7B-instruct model.
Long context Dense
View on Hugging Face →
Overview
Hardware:
L4 RTX-PRO-6000 — drives latency, throughput & cost
Size 1.8B params Tasks /encode License apache-2.0 Latency 261 ms Throughput 12.3K tok/s Cost $0.018 /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: 1,536 Max sequence length 32,768 Inputs text
Benchmarks Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.2961
map at 10 0.2488
mrr at 10 0.2904
Performance L4 b1 c16
Corpus 11.6K tok/s
Corpus p50 178.5ms
Query 2.2K tok/s
Query p50 69.6ms
Reference →
Code search with natural language queries
Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.1225
map at 10 0.0886
mrr at 10 0.0951
Performance L4 b1 c16
Corpus 9.3K tok/s
Corpus p50 96.2ms
Query 1.2K tok/s
Query p50 66.8ms
Reference →
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.2766
map at 10 0.2117
mrr at 10 0.3344
Performance L4 b1 c16
Corpus 11.8K tok/s
Corpus p50 222.9ms
Query 2.1K tok/s
Query p50 73.4ms
Reference →
Question answering on consumer contracts
Corpus: 153 Queries: 396
Quality
ndcg at 10 0.6897
map at 10 0.6244
mrr at 10 0.6268
Performance L4 b1 c16
Corpus 12.3K tok/s
Corpus p50 735.3ms
Query 3.1K tok/s
Query p50 71.9ms
Reference →
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.2547
map at 10 0.0850
mrr at 10 0.4289
Performance L4 b1 c16
Corpus 12.7K tok/s
Corpus p50 384.4ms
Query 821 tok/s
Query p50 90.2ms
Reference →
Smaller subset of the FiQA financial QA dataset
Quality
ndcg at 10 0.6524
map at 10 0.5848
mrr at 10 0.7032
Performance L4 b1 c16
Corpus 11.3K tok/s
Corpus p50 251.5ms
Query 1.9K tok/s
Query p50 88.7ms
Reference →
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.0368
map at 10 0.0196
mrr at 10 0.0683
Performance L4 b1 c16
Corpus 12.4K tok/s
Corpus p50 261.1ms
Query 2.5K tok/s
Query p50 66.4ms
Reference →
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.6056
map at 10 0.5520
mrr at 10 0.5665
Performance L4 b1 c16
Corpus 12.6K tok/s
Corpus p50 370.4ms
Query 3.1K tok/s
Query p50 74.9ms
Reference →
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.3744
map at 10 0.3466
mrr at 10 0.3466
Performance L4 b1 c16
Corpus 12.4K tok/s
Corpus p50 299.2ms
Query 11.4K tok/s
Query p50 421.4ms
Reference →
