Ollama部署Qwen3-Embedding-4B系列：

ollama run dengcao/Qwen3-Embedding-4B:Q4_K_M

ollama run dengcao/Qwen3-Embedding-4B:Q5_K_M

ollama run dengcao/Qwen3-Embedding-4B:Q8_0

ollama run dengcao/Qwen3-Embedding-4B:F16

关于量化版本的说明：

q8_0：与浮点数16几乎无法区分。资源使用率高，速度慢。不建议大多数用户使用。

q6_k：将Q8_K用于所有张量。

q5_k_m：将 Q6_K 用于一半的 attention.wv 和 feed_forward.w2 张量，否则Q5_K。

q5_0： 原始量化方法，5位。精度更高，资源使用率更高，推理速度更慢。

q4_k_m：将 Q6_K 用于一半的 attention.wv 和 feed_forward.w2 张量，否则Q4_K

q4_0：原始量化方法，4 位。

q3_k_m：将 Q4_K 用于 attention.wv、attention.wo 和 feed_forward.w2 张量，否则Q3_K

q2_k：将 Q4_K 用于 attention.vw 和 feed_forward.w2 张量，Q2_K用于其他张量。

根据经验，建议使用 Q5_K_M，因为它保留了模型的大部分性能。或者，如果要节省一些内存，可以使用 Q4_K_M。

license: apache-2.0 base_model: - Qwen/Qwen3-4B-Base

library_name: transformers

Qwen3-Embedding-4B-GGUF

Highlights

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). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

Exceptional Versatility: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58), while the reranking model excels in various text retrieval scenarios.

Comprehensive Flexibility: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.

Multilingual Capability: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.

Model Overview

Qwen3-Embedding-4B-GGUF has the following features:

• Model Type: Text Embedding
• Supported Languages: 100+ Languages
• Number of Paramaters: 4B
• Context Length: 32k
• Embedding Dimension: Up to 2560, supports user-defined output dimensions ranging from 32 to 2560
• Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0, f16

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub.

Qwen3 Embedding Series Model list

Note: - MRL Support indicates whether the embedding model supports custom dimensions for the final embedding. - Instruction Aware notes whether the embedding or reranking model supports customizing the input instruction according to different tasks. - Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.

Usage

📌 Tip: We recommend that developers customize the instruct according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an instruct on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.

llama.cpp

Check out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp. In the following demonstration, we assume that you are running commands under the repository llama.cpp.

You can run Qwen3 Embedding with one command:

./build/bin/llama-embedding -m model.gguf  -p "<your context here><|endoftext|>"  --pooling last --verbose-prompt --embd-normalize 2

Or lunch a server:

./build/bin/llama-server -m model.gguf --embedding --pooling last -ub 8192 --verbose-prompt

📌 Tip: Qwen3 Embedding models default to using the last token as <|endoftext|>, so you need to manually append this token to the end of your own input context. In addition, when running the llama-server, you also need to manually normalize the output embeddings as llama-server currently does not support the --embd-normalize option.

Evaluation

MTEB (Multilingual)

Note: For compared models, the scores are retrieved from MTEB online leaderboard on May 24th, 2025.

MTEB (Eng v2)

C-MTEB (MTEB Chinese)

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3-embedding,
    title  = {Qwen3-Embedding},
    url    = {https://qwenlm.github.io/blog/qwen3/},
    author = {Qwen Team},
    month  = {May},
    year   = {2025}
}