omlx

Model Deployment

jundot/omlx

23.0K2.0KPythonApache-2.0

An AI server for running large models locally on Apple computers, with one-click management from the menu bar, supporting continuous batching and SSD caching.

🧠 Model Deployment🏠 Local Runtime

omlx preview — Preview card generated by GitHub from the repository. Star counts on the card may lag behind the figures above.

Tool Info

Type🐙 Open Source

Stars23.0K

Forks2.0K

LanguagePython

LicenseApache-2.0

Unlock the full analysis — free

You're reading the public preview of omlx. The AI-written pros & cons, use cases, setup guide and audience fit are free with an account — no credit card. Pro adds AI comparisons (50 per 30 days) and member daily & weekly reports.

Compare omlx with alternatives

See how it stacks up against other model deployment tools.

More Tools

tensorflow

201.2K

An open-source machine learning framework that lets developers build and train their own AI models.

ollama

184.2K

A tool that lets you easily run various large language models on your local computer, supporting popular models like DeepSeek, Qwen, and Gemma.

transformers

168.0K

Load and run various pre-trained AI models in Python, covering tasks such as text, image, and audio.

llama.cpp

131.9K

Run large language models offline on your own computer, no internet or expensive GPU required

vllm

93.4K

An open-source inference engine that serves large language models as fast APIs with higher throughput and lower memory use.