jakedahn/qwen3-embeddings-mlx
MLX-powered Qwen3 embedding server for Apple Silicon Macs. Features 0.6B/4B/8B models, 44K tokens/sec throughput, REST API, batch processing, and model hot-swapping, and more
This project provides a local server for generating text embeddings on your Apple Silicon Mac, turning plain text into numerical representations for various AI tasks. It takes text inputs and outputs high-quality embeddings without needing cloud services. This tool is for AI developers and data scientists who need fast, private text processing for applications like semantic search or building Retrieval Augmented Generation (RAG) systems.
No commits in the last 6 months.
Use this if you are an AI developer or data scientist working on an Apple Silicon Mac and need a fast, local, and private way to convert text into embeddings for semantic search, RAG, or content recommendation.
Not ideal if you don't have an Apple Silicon Mac, need to process extremely high volumes of data beyond a single machine's capacity, or are looking for a pre-built SaaS solution rather than a self-hosted API.
Stars
11
Forks
4
Language
Python
License
MIT
Category
Last pushed
Aug 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jakedahn/qwen3-embeddings-mlx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
qdrant/fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Blaizzy/mlx-embeddings
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on...
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