PekingU / object-detection Open weights updated 1 year ago

rtdetr_r50vd

Name: rtdetr_r50vd
Author: PekingU

1. Model Details 2. Model Sources 3. How to Get Started with the Model 4. Training Details 5. Evaluation 6. Model Architecture and Objective 7. Citation

Params

40 M

Context

—

Downloads 30d

194 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 50 days

▲ 4 K in the last 30 days (2.1%)

226 K186 K

Sep 6Sep 22Oct 9Oct 25

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.2 GB	0.7 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: RTDetrForObjectDetection
Parameters: 40 M
Tensor type: F32
Licence: apache-2.0
First seen on the Hub: 2024-05-29
Training datasets: coco
Added to our catalog: 2026-09-06

Compare with any object-detection model

Popular comparisons

table-transformer-structure-recognition 1.3 M rtdetr_r101vd_coco_o365 1.2 M PP-DocLayoutV3_safetensors 932 K yolos-small 707 K detr-resnet-50 210 K rtdetr_r50vd_coco_o365 208 K