vision
DINOv2
Meta self-supervised image feature backbone; parent of DINOv3 and backbone of RF-DETR.
Levelmodel
Classvision
Parameters304.4M
Contextnot in the notes
Released17 Jul 2023
Opennessopen weights permissive
Runs onsingle datacentre GPU, embedded GPU
Statusactive
Lineage
successorfinetune
Where 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, 5 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 Self-supervised ViT
- Total parameters
- 304.4M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 304.4M for dinov2-large; family up to about 1B (unverified)
- Context length
- not in the notes
- Input
- image
- Output
- not in the notes
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 permissive
- Licence
- Apache License 2.0 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, embedded 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, USAModelDINOv2Meta, vision
DINOv2Meta, visionR&D TopicsSelf-Supervised Visual Representation LearningReal-Time Object Detection (YOLO and DETR Lines)
Use CasesSafety (PPE, Hazards, Fatigue)IndustrialVisual Quality Inspection and Defect DetectionIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Bukit Asam TbkIn production, 9 Sep 2026
PT Aneka Tambang Tbk (ANTAM), ferronickelIn production, 9 Sep 2026PLN Indonesia Power with Huawei (PLTU Banten 3 Lontar)Research, 26 Nov 2025
PT Kilang Pertamina Internasional (Pertamina refineries)In production, 17 Oct 2025+5 moreDeployments of these use cases; none names this model.
PT Bukit Asam TbkIn production, 9 Sep 2026PT Aneka Tambang Tbk (ANTAM), ferronickelIn production, 9 Sep 2026PLN Indonesia Power with Huawei (PLTU Banten 3 Lontar)Research, 26 Nov 2025PT Kilang Pertamina Internasional (Pertamina refineries)In production, 17 Oct 2025+5 moreDeployments of these use cases; none names this model.Organisations 1
R&D topics 2
Sources
- huggingface.co/api/models/facebook/dinov2-large https://huggingface.co/api/models/facebook/dinov2-large
- RF-DETR: Neural Architecture Search for Real-Time Detection Transformers arxiv.org https://arxiv.org/html/2511.09554v2
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DINOv2", https://aurion.semai.id/models/meta-dinov2/, records of October 2026.