jina-embeddings-v5-text-small-retrieval-GGUF

Instructions to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jinaai/jina-embeddings-v5-text-small-retrieval-GGUF",
	filename="v5-small-retrieval-F16.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"source_sentence\": \"That is a happy person\",\n    \"sentences\": [\n        \"That is a happy dog\",\n        \"That is a very happy person\",\n        \"Today is a sunny day\"\n    ]\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Ollama:
```
ollama run hf.co/jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
```

Unsloth Studio

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jinaai/jina-embeddings-v5-text-small-retrieval-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jinaai/jina-embeddings-v5-text-small-retrieval-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jinaai/jina-embeddings-v5-text-small-retrieval-GGUF to start chatting

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Docker Model Runner:
```
docker model run hf.co/jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M
```

Lemonade

How to use jinaai/jina-embeddings-v5-text-small-retrieval-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jinaai/jina-embeddings-v5-text-small-retrieval-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.jina-embeddings-v5-text-small-retrieval-GGUF-Q4_K_M

List all available models

lemonade list

jina-embeddings-v5-text-small-retrieval-GGUF

GGUF quantizations of jina-embeddings-v5-text-small-retrieval using llama.cpp. A 677M parameter multilingual embedding model quantized for efficient inference.

Elastic Inference Service | ArXiv | Blog

We highly recommend to first read this blog post for more technical details and customized llama.cpp build.

Overview

jina-embeddings-v5-text Architecture

jina-embeddings-v5-text-small-retrieval is a task-specific embedding model for retrieval, part of the jina-embeddings-v5-text model family.

Feature	Value
Parameters	677M
Task	`retrieval`
Embedding Dimension	1024
Matryoshka Dimensions	32, 64, 128, 256, 512, 768, 1024
Pooling Strategy	Last-token pooling
Base Model	jina-embeddings-v5-text-small

MMTEB Multilingual Benchmark

MTEB English Benchmark

Retrieval Benchmark Results

Usage with llama.cpp

via Elastic Inference Service

The fastest way to use v5-text in production. Elastic Inference Service (EIS) provides managed embedding inference with built-in scaling, so you can generate embeddings directly within your Elastic deployment.

PUT _inference/text_embedding/jina-v5
{
  "service": "elastic",
  "service_settings": {
    "model_id": "jina-embeddings-v5-text-small"
  }
}

See the Elastic Inference Service documentation for setup details.

# Build llama.cpp (upstream)
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp && cmake -B build && cmake --build build --config Release

# Run embedding
./build/bin/llama-embedding -m jina-embeddings-v5-text-small-retrieval-Q8_0.gguf \
  --pooling last -p "Your text here"

License

CC-BY-NC-4.0. For commercial use, please contact us.

Downloads last month: 2,412

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for jinaai/jina-embeddings-v5-text-small-retrieval-GGUF

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

jinaai/jina-embeddings-v5-text-small

Quantized

(11)

this model

Space using jinaai/jina-embeddings-v5-text-small-retrieval-GGUF 1

Collection including jinaai/jina-embeddings-v5-text-small-retrieval-GGUF

jina-embeddings-v5-text

Collection

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 40

Paper for jinaai/jina-embeddings-v5-text-small-retrieval-GGUF

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published Feb 17 • 31