About MedMLX

MedMLX reimplements published medical imaging models in MLX for on-device AI on Apple Silicon. The inference path uses no PyTorch or CUDA.

Read the article Source on GitHub

Article

Sandoval J, Sandoval A Jr, Saleem A. MedMLX: On-Device Medical Imaging AI for Apple Silicon. medRxiv. 2026.

doi:10.64898/2026.10.28.26366762

BibTeX

@article{sandoval2026medmlx,
  title   = {MedMLX: On-Device Medical Imaging AI for Apple Silicon},
  author  = {Sandoval, Joseph and Sandoval, Jr., Alfredo and Saleem, Arsalan},
  journal = {medRxiv},
  year    = {2026},
  doi     = {10.64898/2026.10.28.26366762},
  url     = {https://doi.org/10.64898/2026.10.28.26366762}
}

For developers

The medmlx package provides a Python API, a command-line tool and an MCP server. Each model runtime has its own weights, requirements and install instructions.

GitHub PyPI Hugging Face MCP guide

Intended use

MedMLX is research software. It is not a medical device and is not for clinical use. Model outputs require human review.

Licenses

Code and weights are licensed separately. Each package's README and third-party notices give the terms for both.

Sources and licenses for the homepage images and videos are on the image credits page.

Maintained by Joseph Sandoval and Alfredo Sandoval Jr. (GitHub) in the AI-IR lab at the University of Texas Medical Branch.