CoolFace
Modelpublic

jinaai/jina-embeddings-v5-text-nano-text-matching-mlx

sourceHugging Facecc-by-nc-4.0updated 7mo agoView on Hugging Face
1likes118downloads
Model Card

jina-embeddings-v5-text-nano-text-matching-mlx

MLX port of `jina-embeddings-v5-text-nano-text-matching` for efficient inference on Apple Silicon. For the full-size model, see jina-embeddings-v5-text-small-text-matching-mlx.

Elastic Inference Service | ArXiv | Blog

Model Overview

FeatureValue
Parameters239M
Supported Tasktext-matching
Max Sequence Length8192
Embedding Dimension768
Pooling StrategyLast-token pooling
Base ModelEuroBERT/EuroBERT-210m
FormatMLX float16 safetensors

For training details and evaluation results, see our technical report.

Requirements

bash
pip install mlx tokenizers

Usage

bash
git clone https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-text-matching-mlx
cd jina-embeddings-v5-text-nano-text-matching-mlx
python
import mlx.core as mx
from tokenizers import Tokenizer
from model import JinaEmbeddingModel
import json

with open("config.json") as f:
    config = json.load(f)

model = JinaEmbeddingModel(config)
weights = mx.load("model.safetensors")
model.load_weights(list(weights.items()))

tokenizer = Tokenizer.from_file("tokenizer.json")

texts = [
    "غروب جميل على الشاطئ",  # Arabic
    "海滩上美丽的日落",  # Chinese
    "Un beau coucher de soleil sur la plage",  # French
    "Ein wunderschöner Sonnenuntergang am Strand",  # German
]
embeddings = model.encode(texts, tokenizer, task_type="text-matching")

License

jina-embeddings-v5-text-nano is licensed under CC BY-NC 4.0. For commercial use, please contact sales@jina.ai.

Citation

If you find jina-embeddings-v5-text-nano useful in your research, please cite the following paper:

bibtex
@article{akram2026jina,
  title={jina-embeddings-v5-text: Task-Targeted Embedding Distillation},
  author={Mohammad Kalim Akram and Saba Sturua and Nastia Havriushenko and Quentin Herreros and Michael G{\"u}nther and Maximilian Werk and Han Xiao},
  journal={arXiv preprint arXiv:2602.15547},
  year={2026}
}