---
title: Alibaba-NLP/gte-Qwen2-7B-instruct
description: gte-Qwen2-7B-instruct is the latest model in the gte (General Text Embedding) model family that ranks No.1 in both English and Chinese evalu. Qwen2, 7.6B parameters.
canonical_url: https://superlinked.com/models/alibaba-nlp-gte-qwen2-7b-instruct
last_updated: 2026-06-07
---

# Alibaba-NLP/gte-Qwen2-7B-instruct

gte-Qwen2-7B-instruct is the latest model in the gte (General Text Embedding) model family that ranks No.1 in both English and Chinese evaluations on the Massive Text Embedding Benchmark MTEB benchmark (as of June 16, 2024).

Source: [Alibaba-NLP/gte-Qwen2-7B-instruct on HuggingFace](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Qwen2 |
| Parameters | 7.6B |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 3,584 |
| Max sequence length | 32,000 tokens |
| License | apache-2.0 |
| Inputs | text |

## Benchmarks

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.4040 · map at 10: 0.1548 · mrr at 10: 0.6133

**Performance (L4 b1 c16):** Corpus 3.7K tok/s · Corpus p50 1.1s · Query 228 tok/s · Query p50 361.2ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### NanoFiQA2018Retrieval

Domain: finance · Task: retrieval · Language: en

Smaller subset of the FiQA financial QA dataset

**Quality:** ndcg at 10: 0.6902 · map at 10: 0.6156 · mrr at 10: 0.7338

**Performance (L4 b1 c16):** Corpus 3.3K tok/s · Corpus p50 594.5ms · Query 500 tok/s · Query p50 221.7ms

[Reference](https://sites.google.com/view/fiqa/)