mlxturbo is an open-source MLX inference engine for Apple Silicon devices. It provides a self-hosted server compatible with OpenAI and Anthropic APIs, targeting developers who need local model inference and serving.
mlxturbo is an Inference & model serving project. It focuses on running local machine-learning inference and compatible model-serving APIs efficiently on Apple Silicon. mlxturbo is an open-source project aimed at developers running local AI inference on Apple Silicon. mlxturbo is open source under the MIT license. mlxturbo is available on the command line and API, and it can be self-hosted.
Akakeishin builds and maintains mlxturbo, and it first shipped in 2026. Development happens publicly on GitHub with 145 commits in the last 90 days. Key capabilities include MLX inference, OpenAI API compatibility, and Anthropic API compatibility. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do