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
Download NOTICE from MedMLX/medsam2-mlx: direct link, hf CLI and curl.
- Browser
- Download file 796 Bytes
-
https://huggingface.co/MedMLX/medsam2-mlx/resolve/main/NOTICE
- Command line
-
hf download hf://MedMLX/medsam2-mlx/NOTICE
-
curl -L -o NOTICE https://huggingface.co/MedMLX/medsam2-mlx/resolve/main/NOTICE
796 Bytes
| MedSAM2 source checkpoints: MedSAM2_latest, MedSAM2_2411, MedSAM2_CTLesion, MedSAM2_MRI_LiverLesion, MedSAM2_US_Heart | |
| Original publisher: WangLab; authors: Jun Ma, Zongxin Yang, Sumin Kim, Bihui Chen, Mohammed Baharoon, Adibvafa Fallahpour, Reza Asakereh, Hongwei Lyu, and Bo Wang. | |
| Source: https://huggingface.co/wanglab/MedSAM2/tree/e4a6f35edd7e091619cbc0750f462f1574e23955 | |
| Paper: https://arxiv.org/abs/2504.03600 | |
| The source model card identifies CC-BY-SA-4.0 (LICENSE_CC_BY_SA_4.0.txt): https://creativecommons.org/licenses/by-sa/4.0/ | |
| The same source states that model weights can only be used for research and education. | |
| Changes: MedMLX converted the checkpoints to MLX safetensors without retraining. Retain the source attribution, license link, supplied notices, and indication of changes. | |