Compare all 7 Ultralytics vision models we track, all of them open-weight. Try 4 of them on your own images, free in the Roboflow Playground.
7 models · 7 open-weight · 4 free to try · Updated Oct 2025
Every Ultralytics vision model in our catalog is open-weight. All 7 publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on AGPL 3.0 terms. The newest additions are YOLO26 (Oct 2025) and YOLO11 (Sep 2024). The lineup reaches back to YOLOv5, released Jan 2020.
Between them, the Ultralytics models we list cover 4 distinct vision tasks. The widest coverage is object detection (4 models), instance segmentation (3), and classification (1). For object detection, start with YOLO26, YOLO11, or YOLOv8.
On the open-weight tier, YOLOv8 is the largest at 3.2M-68.2M parameters and YOLOv5 the smallest at 1.9M-86.7M, small enough to run on a single GPU or on-device. All 7 ship under custom or copyleft terms, so read the license before you deploy commercially.
With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. 4 of the 7 Ultralytics vision models run live in the Roboflow Playground, so you can run the same image through several of them and compare the answers before committing to one.
What each of the 7 Ultralytics vision models in our catalog is built for, and how you run it.
7 models with downloadable weights you can self-host under their licenses (AGPL 3.0). 4 run live in the Playground through hosted APIs, so self-hosting is optional.
| Actions | ||||
|---|---|---|---|---|
YOLO26Ultralytics | 2.4M-55.7M | AGPL 3.0 | Oct 2025 | |
YOLO11Ultralytics | 2.6M-56.9M | AGPL 3.0 | Sep 2024 | |
YOLOv8 Pose EstimationUltralytics | 2.9M-57.6M | AGPL 3.0 | Apr 2023 | |
YOLOv8Ultralytics | 3.2M-68.2M | AGPL 3.0 | Jan 2023 | |
YOLOv8 ClassificationUltralytics | — | AGPL 3.0 | Jan 2023 | |
YOLOv8 Instance SegmentationUltralytics | 2.7M-62.8M | AGPL 3.0 | Jan 2023 | |
YOLOv5Ultralytics | 1.9M-86.7M | AGPL 3.0 | Jan 2020 |
4 of the 7 Ultralytics vision models we track handle object detection: YOLO26, YOLO11, YOLOv8, and YOLOv5. Each model page lists its full task coverage, license, and specs.
3 of the 7 Ultralytics vision models we track handle instance segmentation: YOLO26, YOLO11, and YOLOv8 Instance Segmentation. Each model page lists its full task coverage, license, and specs.
Yes. All 7 Ultralytics vision models we track publish downloadable weights you can self-host under their licenses (AGPL 3.0).
We do not publish an Ultralytics-only ranking, so pick on constraints rather than a label. 4 Ultralytics models handle object detection; the most recent is YOLO26 (Oct 2025). Measured scores across every lab we test are on our object detection benchmark, linked at the bottom of this page. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model.
We track 7 live Ultralytics vision models. The most recent addition is YOLO26, released Oct 2025.
Yes. 4 of the 7 Ultralytics models run live in the Roboflow Playground. Upload your own image, run several models on it at once, and compare the outputs side by side. No setup and no account required.
This page lists all 7 Ultralytics vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover object detection, instance segmentation, and classification, among other tasks. 4 of them run live in the Roboflow Playground on your own images. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.