nnunet-mlx
Run pretrained nnU-Net v2 models locally on Apple Silicon with native MLX.
Docs · Supported models · MedMLX
nnU-Net liver model on an AMOS22 CT (left) and BraTS model on a Medical Segmentation Decathlon MRI (right).
| Input | Output |
|---|---|
| NIfTI channels + model folder | Segmentation and optional probabilities |
Apple Silicon · Metal · Python 3.13 / 3.14 · uv
Quick start
uv venv --python 3.13
source .venv/bin/activate
uv pip install "nnunet-mlx[conversion]"
Convert a trusted nnU-Net v2 model folder, then predict:
nnunet-mlx convert model-folder \
--source-model-folder /path/to/upstream-model \
--output-model-folder mlx-model
nnunet-mlx model predict \
--model-folder mlx-model \
--input case_0000.nii.gz \
--output-prefix predictions/case
Supports 2D and 3D PlainConvUNet and ResidualEncoderUNet. Supply input channels in the model’s expected order.
License
Apache-2.0. See third-party notices. Model weights retain their publisher terms.
For research and education. Outputs require human review.
1 maintainer
Metadata
1 maintainer
Release files for nnunet-mlx 0.5.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| nnunet_mlx-0.5.2.tar.gz | 121.3 kB | Without provenance | Details for nnunet_mlx-0.5.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| nnunet_mlx-0.5.2-py3-none-any.whl | Python 3 | none | any | Details for nnunet_mlx-0.5.2-py3-none-any.whl |
Total release size: 276.1 kB
Release files / nnunet_mlx-0.5.2.tar.gz
| Download URL | nnunet_mlx-0.5.2.tar.gz |
|---|---|
| Size | 121.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fb546eeca4b9eed13eab03b5d55d023d029294c992818489b5cfe6a50efc0860
|
|
BLAKE2b-256 checksum How to use checksums |
26f2d8a547e36768811c5ae7c57ed8c73ee2970e843b6477020a4d0efdf0e80c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Release files / nnunet_mlx-0.5.2-py3-none-any.whl
| Download URL | nnunet_mlx-0.5.2-py3-none-any.whl |
|---|---|
| Size | 154.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fe696eb478b82f031cad84b6c6aaac47a249999717bd0f92396e1259e1fb28c0
|
|
BLAKE2b-256 checksum How to use checksums |
a0924c12c8477b29a10f444fe11076ed4dece7237ae008d18624a868f20a000e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Security for nnunet-mlx 0.5.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
