jina-embeddings-v5-text-nano-retrieval-GGUF
GGUF quantizations of jina-embeddings-v5-text-nano-retrieval using llama.cpp. A 239M parameter multilingual embedding model quantized for efficient inference.
Elastic Inference Service | ArXiv | Blog
[!IMPORTANT] We highly recommend to first read this blog post for more technical details and customized llama.cpp build.
Overview
jina-embeddings-v5-text-nano-retrieval is a task-specific embedding model for retrieval, part of the jina-embeddings-v5-text model family.
| Feature | Value |
|---|---|
| Parameters | 239M |
| Task | retrieval |
| Embedding Dimension | 768 |
| Matryoshka Dimensions | 32, 64, 128, 256, 512, 768 |
| Pooling Strategy | Last-token pooling |
| Base Model | jina-embeddings-v5-text-nano |
Usage with llama.cpp
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-nano"
}
}
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-nano-retrieval-Q8_0.gguf \
--pooling last -p "Your text here"
License
CC-BY-NC-4.0. For commercial use, please contact us.