Blaizzy/mlx-embeddings
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.
This tool helps Mac users analyze and compare text and images by converting them into numerical representations called embeddings. You input text, images, or both, and it outputs these embeddings, which can then be used to find similarities or categorize content. It's designed for anyone needing to understand relationships between different pieces of content, like researchers or content analysts.
290 stars. Used by 4 other packages. Available on PyPI.
Use this if you need to process and understand the semantic meaning of text and images on your Mac to find related content or classify information.
Not ideal if you need to perform these analyses on operating systems other than macOS or require real-time processing for extremely high-volume, low-latency applications.
Stars
290
Forks
33
Language
Python
License
—
Category
Last pushed
Feb 09, 2026
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.
Compare
Related tools
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
qdrant/fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Merck/Sapiens
Sapiens is a human antibody language model based on BERT.
amansrivastava17/embedding-as-service
One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques
jkrukowski/swift-embeddings
Run embedding models locally in Swift using MLTensor.