Qwen3-Embedding-4B

Name: Qwen3-Embedding-4B
Author: Alibaba

Embedding modelQwen3

Qwen3-Embedding-4B

Release date: 2025-06-05Updated: 2025-06-06Views: 1,662

Live demoGitHubHugging Face Compare

Parameters

Context length

32K

Multilingual

Supported

Reasoning ability

2/5

Qwen3-Embedding-4B is an AI model published by Alibaba, released on 2025-06-05, for Embedding model, with 4B parameters, and 32K context length, requiring about 8GB storage, with a 69.45 score on MTEB.

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

Qwen3-Embedding-4B

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

32K tokens

Max output length

4K tokens

Model type

Embedding model

Modality (in / out)

Text → Embedding

Release date

2025-06-05

Model file size

8GB

MoE architecture

Total params / Active params

4B / Not applicable

Knowledge cutoff

No data

Qwen3-Embedding-4B

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- Commercial use permitted

GitHub repo

N/A

Hugging Face

huggingface.co/Qwen/Qwen3-Embedding-8B

Live demo

N/A

Qwen3-Embedding-4B

Official resources

Paper

DataLearnerAI blog

N/A

Qwen3-Embedding-4B

API details

API speed

4/5

No public API pricing yet.

Qwen3-Embedding-4B

Benchmark Results

Qwen3-Embedding-4B currently shows benchmark results led by MTEB (2 / 5, score 69.45). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.