Private LLM

A paid app for Mac, iPhone and iPad that runs quantized open models fully on device, with Shortcuts and Siri support.

Visit Private LLM Docs

More in Local Inference

llama.cpp

C/C++ LLM inference with an OpenAI-compatible server.

Llamafile

Single-file executable LLMs.

MLX

Apple's array framework for ML on Apple silicon.

Cortex

Local AI engine from Jan.

Information is summarised in our own words and may be out of date; check the vendor's site for current terms and prices. Not affiliated with Private LLM. Suggest a correction.

Category	Local Inference
Authentication	No auth
Pricing	Paid
Operating System	macOS iOS
Website	https://privatellm.app/en
Docs	https://privatellm.app/en/faq
Last checked	2026-10-14
As JSON	/api/v1/directory/private-llm.json