Ultralytics YOLO11n object detection (COCO) — fast CPU PyTorch inference.

RF-DETR: SOTA Real-Time Object Detection Model

YOLOv10: Real-Time End-to-End Object Detection

Real-Time Open-Vocabulary Object Detection using the xl weights

Best Human detection and Object Detection Background removal.

Real-Time Open-Vocabulary Object Detection

Zero-shot / open vocabulary object detection

High performance and lightweight object detection models

Cut and Learn for unsupervised object detection and instance segmentation

Moondream 3 is a fast, efficient 9B mixture-of-experts vision language model (2B active parameters) that delivers frontier-level visual reasoning for tasks like object detection, pointing, OCR, and structured output.

Ultralytics YOLO26 object detection (COCO), selectable size n/s/m/l/x.

Grounding DINO: zero-shot text-prompted object detection (SwinT-OGC). H100 build.

The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework, achieving higher inference efficiency. Compared with the 3.5-35B-A3B, this model demonstrates significantly improved agentic coding capabilities, mathematical and code reasoning abilities, spatial intelligence, as well as object localization and object detection performance.