vision
SAM 3.1 (Object Multiplex)
SAM 3 update for video multi-object tracking and segmentation.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released27 Mar 2026
Opennessopen weights restricted
Runs onsingle datacentre GPU
Statusactive
Lineage
successorfinetune
SAM 3 is the parent (successor)high confidencemodel cardWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer SAM 3 update with object multiplexing
- Total parameters
- – sourcesunverified
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image, video, text
- Output
- image, video
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- SAM License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperMetabig tech, USA
Metabig tech, USAModelSAM 3.1 (Object Multiplex)Meta, vision
SAM 3.1 (Object Multiplex)Meta, visionR&D TopicsPromptable Segmentation Foundation Models (Segment Anything)Semantic, Instance and Panoptic Segmentation Architectures
Use CasesMedical Image SegmentationHealthcareRobotic Waste and Recycling SortingIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Models 1
Organisations 1
R&D topics 2
Semantic, Instance and Panoptic Segmentation ArchitecturesNetworks that label every pixel of an image by class, by object instance, or both.produced byPromptable Segmentation Foundation Models (Segment Anything)Models that cut out any object from a point, box or text prompt, trained on very large ma…produced by
Sources
- GitHub - facebookresearch/sam3: The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SA github.com https://github.com/facebookresearch/sam3
- SAM 3.1: Segment Anything Model | ComfyUI Wiki comfyui-wiki.com https://comfyui-wiki.com/en/models/sam/sam3.1
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SAM 3.1 (Object Multiplex)", https://aurion.semai.id/models/meta-sam-3-1/, records of October 2026.