hanxiao/flash-kmeans-mlx
IO-aware batched K-Means for Apple Silicon, ported from Flash-KMeans (Triton/CUDA) to pure MLX. Up to 94x faster than sklearn.
This tool helps you quickly group large collections of data points, like customer segments or image features, into distinct clusters on your Apple Silicon Mac. You input your raw data, and it outputs which cluster each data point belongs to and the central point (centroid) of each cluster. This is designed for data scientists, machine learning engineers, and researchers working with large datasets who need to perform K-Means clustering efficiently.
Available on PyPI.
Use this if you need to rapidly cluster very large datasets with K-Means on an Apple Silicon device, especially if you're working with data for machine learning, image analysis, or text processing.
Not ideal if you are working with extremely small datasets, do not have an Apple Silicon Mac, or require clustering algorithms other than K-Means.
Stars
11
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hanxiao/flash-kmeans-mlx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...
mlcommons/inference
Reference implementations of MLPerf® inference benchmarks
mlcommons/training
Reference implementations of MLPerf® training benchmarks
datamade/usaddress
:us: a python library for parsing unstructured United States address strings into address components
GRAAL-Research/deepparse
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning