Instructions to use MedMLX/medsam2-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use MedMLX/medsam2-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download MedMLX/medsam2-mlx --local-dir medsam2-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Link and cite the MedMLX paper
Browse files
README.md
CHANGED
|
@@ -23,3 +23,17 @@ weights = hf_hub_download("MedMLX/medsam2-mlx", "MedSAM2_CTLesion.safetensors")
|
|
| 23 |
```
|
| 24 |
|
| 25 |
The [upstream model card](https://huggingface.co/wanglab/MedSAM2) identifies the weights as CC BY-SA 4.0 and states that they may only be used for research and education. See the [license terms](https://creativecommons.org/licenses/by-sa/4.0/legalcode.en) and upstream model card. Outputs require human review.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
```
|
| 24 |
|
| 25 |
The [upstream model card](https://huggingface.co/wanglab/MedSAM2) identifies the weights as CC BY-SA 4.0 and states that they may only be used for research and education. See the [license terms](https://creativecommons.org/licenses/by-sa/4.0/legalcode.en) and upstream model card. Outputs require human review.
|
| 26 |
+
|
| 27 |
+
## Citation
|
| 28 |
+
|
| 29 |
+
If you use MedMLX, please cite the [MedMLX paper](https://doi.org/10.64898/2026.10.28.26366762):
|
| 30 |
+
|
| 31 |
+
```bibtex
|
| 32 |
+
@article{sandoval2026medmlx,
|
| 33 |
+
title = {MedMLX: On-Device Medical Imaging AI for Apple Silicon},
|
| 34 |
+
author = {Sandoval, A. and Sandoval, J. and Saleem, A.},
|
| 35 |
+
journal = {medRxiv},
|
| 36 |
+
year = {2026},
|
| 37 |
+
doi = {10.64898/2026.10.28.26366762}
|
| 38 |
+
}
|
| 39 |
+
```
|