Supported Models

All models you can deploy with Roboflow.

With Roboflow, you can deploy object detection, segmentation, classification, keypoint, and multimodal models.

All of these models can be deployed with Workflows using:

• Serverless Hosted API V2

• Serverless Hosted API

• Dedicated Deployment (CPU or GPU)

• Roboflow Inference

The table below shows common models and their support for training, model weights upload and model weights export/download.

Model	Task Type(s)	Training Supported on Roboflow?	Model Weights Upload Supported?	Model Weights Export Supported?
Roboflow 3.0	Object Detection, Classification, Keypoint Detection, Instance Segmentation, Semantic Segmentation
RF-DETR	Object Detection
YOLOv12	Object Detection
YOLO11	Object Detection, Instance Segmentation, Keypoint Detection
YOLOv9	Object Detection
YOLOv8	Object Detection, Instance Segmentation, Keypoint Detection
YOLOv7	Instance Segmentation
YOLOv5	Object Detection, Instance Segmentation
ViT	Classification
ResNet	Classification
Florence 2	Multimodal
PaliGemma 2	Multimodal, Object Detection
Qwen2.5-VL	Multimodal
SmolVLM2	Multimodal
SmolVLM 256M	Multimodal
CLIP	Multimodal
Segment Anything	Multimodal
Segment Anything 2	Multimodal
Moondream 2	Multimodal
YOLO-World	Multimodal
Grounding DINO	Multimodal
Gaze Detection	Gaze Detection
Depth Anything v2	Depth Estimation
TR-OCR	Optical Character Recognition