jjang-ai/vmlx

vMLX - Cont Batch, Prefix, Paged, KV Cache Quant, VL - Powers MLX Studio. Image gen/edit, OpenAI/Anth

44
/ 100
Emerging

vMLX transforms your Apple Silicon Mac into a powerful local AI engine, letting you run large language models and image generation models right on your machine. You can input text prompts or images and receive generated text, code, or new images, all without sending data to the cloud. This is designed for researchers, developers, and power users who need to work with advanced AI models privately and efficiently on their macOS devices.

Available on PyPI.

Use this if you need to run cutting-edge AI models like LLMs, VLMs, or image generators directly on your Apple Silicon Mac, ensuring privacy and control over your data.

Not ideal if you don't have an Apple Silicon Mac, or if your projects require massive scale-out across many GPUs beyond a single machine.

local-AI machine-learning-development private-data-analysis AI-model-experimentation on-device-inference
Maintenance 13 / 25
Adoption 6 / 25
Maturity 20 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Mar 18, 2026

Commits (30d)

0

Dependencies

19

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/jjang-ai/vmlx"

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