# detr-resnet-101 by AI at Meta: Open-Weight Model Source: https://savrn.com/models/detr-resnet-101 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve detr-resnet-101 (61M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [detr-resnet-101 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/detr-resnet-101/gpus) ## Model Card By AI at Meta, published under apache-2.0, revision 7d14702e444d. ### DETR (End-to-End Object Detection) model with ResNet-101 backbone DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper [End-to-End Object Detection with Transformers](https://savrn.com/papers/end-to-end-object-detection-with-transformers) by Carion et al. and first released in [this repository](https://github.com/facebookresearch/detr). Disclaimer: The team releasing DETR did not write a model card for this model so this model card has been written by the Hugging Face team. ### Model description The DETR model is an encoder-decoder transformer with a convolutional backbone. Two heads are added on top of the decoder outputs in order to perform object detection: a linear layer for the class labels and a MLP (multi-layer perceptron) for the bounding boxes. The model uses so-called object queries to detect objects in an image. Each object query looks for a particular object in the image. For COCO, the number of object queries is set to 100. [Read the full model card (684 words)](https://savrn.com/models/detr-resnet-101/card) ## Configuration Architecture DetrForObjectDetection Context length (tokens) 1,024 Layers 6 Model type detr ## Identity and Version Repository facebook/detr-resnet-101 Publisher AI at Meta Task Object detection Modality Image Library transformers Parameters 61M parameters Languages Not stated by the source Revision 7d14702e444d98d0b1764824567fc2b45e1eb218 First published 2022-03-02 Last updated 2023-12-14 ## Files and Weights 6 files, 485.8 MB in total. The weights are 2 files totalling 485.8 MB in bin, safetensors. Weights2 files · 485.8 MB Configuration2 files · 4.6 KB Documentation1 file · 5.9 KB Repository1 file · 744 B Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 242.8 MB | 86cec5ddf787 | | pytorch_model.bin | Weights | 243.0 MB | 0943b5a9085a | | config.json | Configuration | 4.4 KB | — | | preprocessor_config.json | Configuration | 255 B | — | | README.md | Documentation | 5.9 KB | — | | .gitattributes | Repository | 744 B | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 485.8 MB [Download from AI at Meta](https://huggingface.co/facebook/detr-resnet-101) Released by AI at Meta through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2005.12872](https://savrn.com/papers/end-to-end-object-detection-with-transformers) - Trained on (disclosed) coco ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 485.8 MB | | 16-bit | 0.1 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About detr-resnet-101 ### How much GPU memory does detr-resnet-101 need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (61M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run detr-resnet-101 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use detr-resnet-101 commercially? Yes. detr-resnet-101 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is detr-resnet-101's context length? 1,024 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Object detection ### [dfine-xlarge-coco](https://savrn.com/models/dfine-xlarge-coco) [University of Science and Technology of China](https://savrn.com/model-publishers/ustc-community) The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global… Open weights apache-2.0 63M parameters transformers [View model](https://savrn.com/models/dfine-xlarge-coco) Model · Object detection ### [dfine-xlarge-obj2coco](https://savrn.com/models/dfine-xlarge-obj2coco) [University of Science and Technology of China](https://savrn.com/model-publishers/ustc-community) The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global… Open weights apache-2.0 63M parameters transformers [View model](https://savrn.com/models/dfine-xlarge-obj2coco) Model · Object detection ### [YOLO-Face-Person-Detector](https://savrn.com/models/yolo-face-person-detector) [Irina Tolstykh](https://savrn.com/model-publishers/iitolstykh) This model is a fine-tuned version of YOLOv8x specialized in detecting two specific classes: Face and Person. It has been trained on a large-scale proprietary dataset consisting of approximately 150,000 images. The high capacity of the YOLOv8x architecture combined with a diverse proprietary dataset ensures high accuracy and robustness in various scenarios. You can load the model using the Hugging Face transformers library by enabling custom code execution. If you prefer the standard Ultralytics API, you can download the weights from the Hub and load them directly. This method automatically handles model downloading for ultralytics YOLO model. This model is based on the Ultralytics YOLOv8… Open weights agpl-3.0 68M parameters ultralytics [View model](https://savrn.com/models/yolo-face-person-detector) Model · Object detection ### [rt-detr-finetuned-for-satellite-image-roofs-detection](https://savrn.com/models/rt-detr-finetuned-for-satellite-image-roofs-detection) [YifengLiu](https://savrn.com/model-publishers/yifeng-liu) Roof detection model for remote sensing imagery, fine-tuned using RT-DETR. The following example shows roof detections produced by the model: Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Open weights mit 77M parameters transformers [View model](https://savrn.com/models/rt-detr-finetuned-for-satellite-image-roofs-detection) Model · Object detection ### [rtdetr_r101vd_coco_o365](https://savrn.com/models/rtdetr-r101vd-coco-o365) [Peking University](https://savrn.com/model-publishers/pekingu) However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy.… Open weights apache-2.0 77M parameters transformers [View model](https://savrn.com/models/rtdetr-r101vd-coco-o365) Model · Object detection ### [rtdetr_v2_r101vd](https://savrn.com/models/rtdetr-v2-r101vd) [Peking University](https://savrn.com/model-publishers/pekingu) The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf This is RT-DETRv2 consistently outperforms its predecessor across all… Open weights apache-2.0 77M parameters transformers [View model](https://savrn.com/models/rtdetr-v2-r101vd) ## AI at Meta [All models and datasets](https://savrn.com/model-publishers/facebook) ## Versions - [7d14702e444d](https://savrn.com/models/detr-resnet-101/versions/7d14702e444d) · current 2026-09-18 ## Explore More - [All object detection models](https://savrn.com/models/tasks/object-detection) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-21. - [AI at Meta website](https://ai.meta.com/resources/models-and-libraries/) - [Hugging Face record](https://huggingface.co/facebook/detr-resnet-101) - [How the hub is built](https://savrn.com/model-hub/methodology)