# oMLX

> Serve local AI models on Apple silicon with persistent caching.

oMLX is an MLX-based inference server for Apple silicon Macs. It stores reusable model cache blocks on SSD as well as in memory, allowing previous prompt prefixes to be restored across requests and server restarts. Continuous batching supports concurrent work, and the server can manage language, vision-language, embedding, and reranking models.

A native menu-bar app controls the server, while a web dashboard provides model downloads, chat, and operating metrics. OpenAI-compatible and Anthropic-compatible endpoints let existing coding tools use the local backend. Users can point oMLX at supported model folders they already have. The project is open source and also includes configurable tool-calling and MCP integration.

## Listing details

- Canonical BetaNeon page: https://betaneon.com/products/omlx
- Official website: https://omlx.ai/
- Category: Artificial intelligence / Local AI & model runners
- Status: Launched
- Topics: AI, Developer tools, Open source, Prompts, macOS
- Listing updated: 2026-10-30T16:52:36.626Z
- Information source: https://omlx.ai/

This is a product introduction, not an endorsement. Confirm current availability, features, and prices on the official website. Community upvotes on BetaNeon are not star ratings.