rtdetr_r50vd_coco_o365
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve PekingU/rtdetr_r50vd_coco_o365New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
rtdetr_r50vd_coco_o365 is an open-weight object detection model published by PekingU on Hugging Face in May 2024, with 40M parameters under the apache-2.0 license.
Among the 24 object detection models in this directory it ranks 16th by monthly Hugging Face downloads, and 11 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.
Similar object detection modelsLink to this section
- rtdetr_r50vd - 40M, 230,380 downloads/month
- detr-doc-table-detection - 40M, 138,685 downloads/month
- DETR ResNet-50 - 40M, 113,423 downloads/month
- rtdetr_v2_r50vd - 40M, 75,475 downloads/month
- fashion-object-detection - 40M, 17,884 downloads/month
PopularityLink to this section
rtdetr_r50vd_coco_o365 was downloaded 76,988 times on Hugging Face in the last month (3,020,350 all-time) and has 18 likes.
Run it locallyLink to this section
Weights and usage instructions are on the PekingU/rtdetr_r50vd_coco_o365 model card; it loads with Hugging Face Transformers.
Local runtimes that fit this model:
- transformers - the reference Python library most model cards target
PaperLink to this section
From the community
What users are saying
“As stated on the page here (https://docs.ultralytics.com/models/rtdetr/), RT-DETR is based on the idea of DETR (the NMS-free framework) so it really doesn't include NMS. Therefore even the ONNX model cannot contain NMS operations after export from RT-DETR.”
Frequently asked
Quick answers to common questions
How much VRAM does rtdetr_r50vd_coco_o365 need?
rtdetr_r50vd_coco_o365 with 40M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is rtdetr_r50vd_coco_o365 better than other PekingU models?
rtdetr_r50vd_coco_o365 has 40M parameters - a strong choice for object-detection.
What license is rtdetr_r50vd_coco_o365 under?
rtdetr_r50vd_coco_o365 is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs rtdetr_r50vd_coco_o365 well?
With 40M parameters, rtdetr_r50vd_coco_o365 is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.
What is the best quantization for rtdetr_r50vd_coco_o365?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with rtdetr_r50vd_coco_o365?
rtdetr_r50vd_coco_o365 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec