GME-Qwen2-VL-2B

Name: gme-Qwen2-VL-2B
Author: Alibaba

Embedding modelQwen2

gme-Qwen2-VL-2B

Release date: 2024-12-24Updated: 2026-01-09Views: 218

Live demoGitHubHugging Face Compare

Parameters

Context length

32K

Multilingual

No data

Reasoning ability

3/5

gme-Qwen2-VL-2B is an AI model published by Alibaba, released on 2024-12-24, for Embedding model, with 2B parameters, and 32K context length, requiring about 8.85 GB storage, with a 51.89 score on MMEB-v2-Image.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GME-Qwen2-VL-2B

Model basics

Reasoning traces

No data

Thinking modes

Standard Mode (Default)Thinking Mode

Context length

32K tokens

Max output length

No data

Model type

Embedding model

Modality (in / out)

Text, Image, Embedding → Embedding

Release date

2024-12-24

Model file size

8.85 GB

MoE architecture

Total params / Active params

2B / Not applicable

Knowledge cutoff

No data

GME-Qwen2-VL-2B

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- Commercial use permitted

GitHub repo

N/A

Hugging Face

huggingface.co/Alibaba-NLP/gme-Qwen2-VL-2B-Inst…

Live demo

N/A

GME-Qwen2-VL-2B

Official resources

Paper

DataLearnerAI blog

N/A

GME-Qwen2-VL-2B

API details

API speed

3/5

No public API pricing yet.

GME-Qwen2-VL-2B

Benchmark Results

GME-Qwen2-VL-2B currently shows benchmark results led by MMEB-v2-Image (6 / 6, score 51.89). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.