Instructions to use avencera/sam3-image-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use avencera/sam3-image-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir sam3-image-mlx avencera/sam3-image-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
SAM 3 image MLX runtime
This repository is an Avencera mirror of the MLX SAM 3 image runtime files. It provides stable launch acquisition from an Avencera-owned repository.
The weight and index files are byte-for-byte copies from
mlx-community/sam3-image at revision
b72a14d8127e17e6f2a3d2e075bbbf4307ba146e. Avencera did not convert or
modify them. They derive from facebook/sam3 at revision
3c879f39826c281e95690f02c7821c4de09afae7.
These files are SAM Materials and are available only under the included SAM License. By using or distributing any part of them, you agree to that license.
See PROVENANCE.json for the locked source revisions and file hashes.
Model size
0.8B params
Tensor type
F32
·
C64 ·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for avencera/sam3-image-mlx
Base model
facebook/sam3