visionfamily
YOLO26
Ultralytics real-time vision model family (n/s/m/l/x) for detection, segmentation, semantic segmentation, depth, classification, pose, OBB and open-vocabulary variants. Follows YOLO11; the NMS-free idea is traced to YOLOv10.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
ReleasedJan 2026
Opennessopen source
Runs onCPU server, laptop, embedded GPU, single datacentre GPU
Statusactive
Benchmark Results
vendor-reported
COCO val valdomain
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
successorfinetune
YOLOv10 is the parent (successor)low confidencenotesWhere 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.
Industry Use Cases
R&D Topics
Identity
- Developer
- Ultralytics
- Family
- not in the notes
- Released
- Jan 2026 sourcesannouncement page
- Weights published
- –
- Record checked
- 10 Oct 2026
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
- CNN CNN YOLO; DFL removed; optional NMS-free end-to-end head; MuSGD optimiser (SGD + Muon hybrid); ProgLoss + STAL
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 2.4M (n) to 55.7M (x) fused
- Context length
- not in the notes
- Input
- image
- Output
- image, text
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 source
- Licence
- GNU Affero General Public License v3.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- CPU server, laptop, embedded GPU, single datacentre GPU
- Footprint
- n: 38.9 ms CPU ONNX; x: 11.8 ms T4 TensorRT. Also available under an Ultralytics Enterprise licence. Tier fit is a judgement.
- 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.
Links
Developer
Ultralyticscompany, USA
Model
YOLO26Ultralytics, vision
Use CasesSafety (PPE, Hazards, Fatigue)IndustrialVisual Quality Inspection and Defect DetectionIndustrial
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 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.Use cases 2
Models 8
Organisations 1
Sources
- Models Supported by Ultralytics | Ultralytics Docs docs.ultralytics.com https://docs.ultralytics.com/yolo/
- Ultralytics YOLO26 | Ultralytics Docs docs.ultralytics.com https://docs.ultralytics.com/models/yolo26/
- Ultralytics Team ultralytics.com https://ultralytics.com/about
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "YOLO26", https://aurion.semai.id/models/ultralytics-yolo26/, records of October 2026.