Search + Filter
omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Updated means this listing was last refreshed on Mar 12, 2026.
About omlx
Pricing:Freemium
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar jundot/omlx is an open source project on GitHub with 3,368 stars. Built primarily in Python. Licensed under Apache-2.0. Topics: apple-silicon, inference-server, llm, macos, mlx, openai-api.
Pros
- •Accessible pricing model for early testing.
Cons
- •Pricing details are limited and may require visiting the official website.
- •Limited public review volume, so performance may vary by workflow.
- •No screenshots provided for quick visual evaluation.