SAM3.1 CoreML FP16
SAM 3 (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points,...
Model source
- Kind
- Other
- File size
- 61.2–877 MB
- Base model
- facebook/sam3.1
- Version
- vRevision b211f08
- Updated
- Oct 10, 2026
- Downloads
- 6
- Source
- Hugging Face
Source description
SAM 3.1 Core ML (FP16)
SAM 3 (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points, boxes, and masks. Compared to its predecessor SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase or exemplars. Unlike prior work, SAM 3 can handle a vastly larger set of open-vocabulary prompts. It achieves 75-80% of human performance on our new SA-CO benchmark which contains 270K unique concepts, over 50 times more than existing benchmarks. SAM 3.1 builds on this with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers ~7x faster inference at 128 objects on a single H100 GPU without sacrificing accuracy, along with improved VOS performance on 6 out of 7 benchmarks.
This is the Core ML (FP16) version of SAM 3.1 · Code.
Download
Install huggingface-cli
brew install huggingface-cli
huggingface-cli download --local-dir models AllanVester/SAM3.1-CoreML-FP16
Citation
If you use SAM 3 in your research, please use the following BibTeX entry:
@misc{carion2025sam3segmentconcepts,
title={SAM 3: Segment Anything with Concepts},
author={Nicolas Carion and Laura Gustafson and Yuan-Ting Hu and Shoubhik Debnath and Ronghang Hu and Didac Suris and Chaitanya Ryali and Kalyan Vasudev Alwala and Haitham Khedr and Andrew Huang and Jie Lei and Tengyu Ma and Baishan Guo and Arpit Kalla and Markus Marks and Joseph Greer and Meng Wang and Peize Sun and Roman Rädle and Triantafyllos Afouras and Effrosyni Mavroudi and Katherine Xu and Tsung-Han Wu and Yu Zhou and Liliane Momeni and Rishi Hazra and Shuangrui Ding and Sagar Vaze and Francois Porcher and Feng Li and Siyuan Li and Aishwarya Kamath and Ho Kei Cheng and Piotr Dollár and Nikhila Ravi and Kate Saenko and Pengchuan Zhang and Christoph Feichtenhofer},
year={2025},
eprint={2511.16719},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.16719},
}
License
The original SAM 3.1 model weights are released by Meta under the SAM License, a custom permissive license for commercial and research use.
Sources
1 source
Sources
1 sourceVerified Oct 10
Download files
Model artifacts
3 artifacts
Model artifacts
3 artifactsSAM3.1_Detector_FP16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
bin · 61.2 MB · SHA-256 edf5213df00d…02be · Hugging Face
Download fileSAM3.1_ImageEncoder_FP16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
bin · 877 MB · SHA-256 e957fa30bcd5…ca05 · Hugging Face
Download fileSAM3.1_TextEncoder_FP16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
bin · 674 MB · SHA-256 65ffb8bfd0cb…8505 · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: other language: - en pipeline_tag: mask-generation base_model: facebook/sam3.1 library_name: coreml tags: - coreml - sam3 - sam3.1 - segmentation - detection - tracking - object-multiplex - fp16 - float16 --- # SAM 3.1 Core ML (FP16) [SAM 3](https://github.com/facebookresearch/sam3) (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points, boxes, and masks. Compared to its predecessor [SAM 2](https://github.com/facebookresearch/sam2), SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase or exemplars. Unlike prior work, SAM 3 can handle a vastly larger set of open-vocabulary prompts. It achieves 75-80% of human performance on our new SA-CO benchmark which contains 270K unique concepts, over 50 times more than existing benchmarks. SAM 3.1 builds on this with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers ~7x faster inference at 128 objects on a single H100 GPU without sacrificing accuracy, along with improved VOS performance on 6 out of 7 benchmarks. This is the Core ML (FP16) version of [SAM 3.1](https://huggingface.co/facebook/sam3.1) · [Code](https://github.com/facebookresearch/sam3). ## Download Install `huggingface-cli` ```bash brew install huggingface-cli ``` ```bash huggingface-cli download --local-dir models AllanVester/SAM3.1-CoreML-FP16 ``` ## Citation If you use SAM 3 in your research, please use the following BibTeX entry: ``` @misc{carion2025sam3segmentconcepts, title={SAM 3: Segment Anything with Concepts}, author={Nicolas Carion and Laura Gustafson and Yuan-Ting Hu and Shoubhik Debnath and Ronghang Hu and Didac Suris and Chaitanya Ryali and Kalyan Vasudev Alwala and Haitham Khedr and Andrew Huang and Jie Lei and Tengyu Ma and Baishan Guo and Arpit Kalla and Markus Marks and Joseph Greer and Meng Wang and Peize Sun and Roman Rädle and Triantafyllos Afouras and Effrosyni Mavroudi and Katherine Xu and Tsung-Han Wu and Yu Zhou and Liliane Momeni and Rishi Hazra and Shuangrui Ding and Sagar Vaze and Francois Porcher and Feng Li and Siyuan Li and Aishwarya Kamath and Ho Kei Cheng and Piotr Dollár and Nikhila Ravi and Kate Saenko and Pengchuan Zhang and Christo...
Source context: 6 downloads · 0 likes · Pipeline mask-generation · Library coreml · Repo dustbeast/SAM3.1-CoreML-FP16
Source context: 0 downloads · 0 likes · Pipeline mask-generation · Library coreml · Repo dustbeast/SAM3.1-CoreML-FP16
