Runs an LLM inference server on a Mac
oMLX turns a Mac into an LLM inference server run from the menu bar.
Coding / product dossier
oMLX
Runs local text, vision, OCR, embedding, and reranker models as a Mac LLM server.
Product brief
What oMLX does.
oMLX turns your Mac into a full LLM inference server, run from the menu bar. It serves text, vision, OCR, embedding and reranker models with continuous batching, plus a RAM+SSD tiered KV cache that survives restarts, so Claude Code and Cursor respond in about 5s instead of 90s. OpenAI and Anthropic compatible APIs drop straight in. Native Swift, not Electron. Apache 2.0, open source.
Why we selected it
A focused, open-source local inference server with text, vision, OCR, embedding, and reranking support. OpenAI- and Anthropic-compatible APIs make it a practical way for Mac-based builders to test or run local model
- Best for
- Mac-based AI developers
- Category
- Coding
- Daily picks
- 1
- First selected
- 2026-08-30
Product preview saved with our daily selection
Capability scan
What it can help with.
Only capabilities supported by the product information we collected are listed here.
Serves multiple model types
It serves text, vision, OCR, embedding, and reranker models.
Uses continuous batching
oMLX includes continuous batching.
Maintains a tiered KV cache across restarts
It uses a RAM-and-SSD tiered KV cache that survives restarts.
Provides compatible APIs
oMLX offers OpenAI- and Anthropic-compatible APIs.
Best-fit use cases
Run text, vision, OCR, embedding, or reranker models through a Mac-based inference server.
Connect software that uses OpenAI-compatible APIs to a local oMLX server.
Connect software that uses Anthropic-compatible APIs to a local oMLX server.
Experiment with a modifiable open-source LLM server on a Mac.
FAQ
Before you open it.
What is oMLX?
oMLX is a Mac LLM inference server operated from the menu bar.
What model types can oMLX serve?
It serves text, vision, OCR, embedding, and reranker models.
Which API formats does oMLX support?
The product description states that it provides OpenAI- and Anthropic-compatible APIs.
What caching does oMLX use?
It uses a tiered KV cache across RAM and SSD that survives restarts.
Is oMLX open source?
Yes. It is described as open source under the Apache 2.0 license.