Blaizzy/mlx-embeddings

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

69
/ 100
Established

Supports multiple embedding model architectures (BERT, RoBERTa, ModernBERT, Qwen3-VL, Llama variants) and performs both unimodal text and multimodal text-image embedding generation via MLX framework. Provides batch processing capabilities with semantic similarity computation and task-specific functions like masked language modeling and sequence classification. Integrates with HuggingFace-compatible tokenizers and uses mean pooling or config-specified strategies for dense vector generation suitable for retrieval and reranking workflows.

290 stars and 20,666 monthly downloads. Used by 4 other packages. Available on PyPI.

Maintenance 10 / 25
Adoption 24 / 25
Maturity 18 / 25
Community 17 / 25

How are scores calculated?

Stars

290

Forks

33

Language

Python

License

Last pushed

Feb 09, 2026

Monthly downloads

20,666

Commits (30d)

0

Dependencies

4

Reverse dependents

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Blaizzy/mlx-embeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.