Overview
5 featuresIn the Inference & model serving space, mlx-serve takes a focused approach. It enables local, fast, and private inference for MLX models on Apple Silicon devices without relying on cloud APIs. mlx-serve is an open-source project aimed at ai developers and researchers using apple silicon. mlx-serve is open source under the MIT license. It ships for the web, the command line, and API, and it can be self-hosted.
raspoli builds and maintains mlx-serve, and it first shipped in 2026. Development happens publicly on GitHub with 7 commits in the last 90 days. Among its 5 catalogued features are local inference, model hot-swapping, and Apple Silicon support. It exposes integrations via a public API.
- ✓Local inference
- ✓Model hot-swapping
- ✓Apple Silicon support
- ✓OpenAI API compatible
- ✓Supports LLM, vision, TTS, STT
Tagslocal-inferencemlx-modelsopenai-compatible
AI capabilitiesTextImageAudio
Inference: LocalWeights: Open
Built with & integrations
Runs onBrowserCLIAPI-onlySelf-hosted
Indexing history
1What PulseGate has recorded for this listing
Indexed17 Jun · 16:44 UTC
Listing verified against its public source
Frequently asked questions about mlx-serve
- What does mlx-serve do?
- Mlx-serve enables local, fast, and private inference for MLX models on Apple Silicon devices without relying on cloud APIs. It is catalogued under Inference & model serving on PulseGate.
- Who should use mlx-serve?
- mlx-serve is an open-source project built for ai developers and researchers using apple silicon.
- Is mlx-serve free?
- Yes — mlx-serve is open source under the MIT license and free to use.
- What platforms does mlx-serve run on?
- mlx-serve runs on the web, the command line, and API. It can also be self-hosted.
- Is mlx-serve still maintained?
- The GitHub repository shows 7 commits in the last 90 days.
- Who makes mlx-serve?
- mlx-serve is developed by raspoli.
- When did mlx-serve launch?
- mlx-serve first shipped in 2026.