# mask2former-swin-small-coco-instance by AI at Meta Source: https://savrn.com/models/mask2former-swin-small-coco-instance Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve mask2former-swin-small-coco-instance (69M 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 | 0.2 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. [mask2former-swin-small-coco-instance on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/mask2former-swin-small-coco-instance/gpus) ## Model Card Mask2Former model trained on COCO instance segmentation (small-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Excerpt from the card by AI at Meta, licensed other. ## Configuration Architecture Mask2FormerForUniversalSegmentation Layers 10 Attention heads 8 Stored precision float32 Model type mask2former ## Identity and Version Repository facebook/mask2former-swin-small-coco-instance Publisher AI at Meta Task Image segmentation Modality Image Library transformers Parameters 69M parameters Languages Not stated by the source Revision 1b7ac418a0f3cb5edfc5037e488d53587b8bb76b First published 2022-12-26 Last updated 2023-09-07 ## Files and Weights 6 files, 551.3 MB in total. The weights are 2 files totalling 551.2 MB in bin, safetensors. Weights2 files · 551.2 MB Configuration2 files · 80.3 KB Documentation1 file · 3.2 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 275.5 MB | 4ad6f6fb26ce | | pytorch_model.bin | Weights | 275.7 MB | 8585f734ad50 | | config.json | Configuration | 79.8 KB | — | | preprocessor_config.json | Configuration | 537 B | — | | README.md | Documentation | 3.2 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License other Access Open weights, no gate Download size 551.2 MB [Download from AI at Meta](https://huggingface.co/facebook/mask2former-swin-small-coco-instance) Released by AI at Meta through its official repository on Hugging Face. ## Built From - Described by [arXiv:2107.06278](https://savrn.com/papers/per-pixel-classification-is-not-all-you-need-for-semantic-segmentation) - Described by [arXiv:2112.01527](https://savrn.com/papers/masked-attention-mask-transformer-for-universal-image-segmentation) - Trained on (disclosed) coco ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 551.2 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 mask2former-swin-small-coco-instance ### How much GPU memory does mask2former-swin-small-coco-instance need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (69M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run mask2former-swin-small-coco-instance 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. ### What license is mask2former-swin-small-coco-instance released under? other, as its publisher declares it. Read the license text before commercial use. ## Similar Models Model · Image segmentation ### [mask2former-swin-small-ade-semantic](https://savrn.com/models/mask2former-swin-small-ade-semantic) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on ADE20k semantic segmentation (small-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 69M parameters transformers [View model](https://savrn.com/models/mask2former-swin-small-ade-semantic) Model · Image segmentation ### [fashn-human-parser](https://savrn.com/models/fashn-human-parser) [FASHN](https://savrn.com/model-publishers/fashn-ai) A SegFormer-B4 model fine-tuned for human parsing with 18 semantic classes, optimized for fashion and virtual try-on applications. This model segments human images into 18 semantic categories including body parts (face, hair, arms, hands, legs, feet, torso), clothing items (top, dress, skirt, pants, belt, scarf), and accessories (bag, hat, glasses, jewelry). The pipeline automatically manages GPU/CPU and returns per-class masks at the original image resolution. For maximum accuracy, use our Python package which implements the exact preprocessing used during training: The package uses cv2.INTERAREA for resizing (matching training), while the HuggingFace pipeline uses PIL LANCZOS. Labels… Open weights other 64M parameters transformers [View model](https://savrn.com/models/fashn-human-parser) Model · Image segmentation ### [upernet-convnext-tiny](https://savrn.com/models/upernet-convnext-tiny) [OpenMMLab](https://savrn.com/model-publishers/openmmlab) UperNet framework for semantic segmentation, leveraging a ConvNeXt backbone. UperNet was introduced in the paper Unified Perceptual Parsing for Scene Understanding by Xiao et al. Combining UperNet with a ConvNeXt backbone was introduced in the paper A ConvNet for the 2020s. Disclaimer: The team releasing UperNet + ConvNeXt did not write a model card for this model so this model card has been written by the Hugging Face team. UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) and a Pyramid Pooling Module (PPM). Any visual backbone can be plugged into the UperNet framework. The framework predicts a… Open weights mit 60M parameters transformers [View model](https://savrn.com/models/upernet-convnext-tiny) Model · Image segmentation ### [face-parsing](https://savrn.com/models/face-parsing) [Jonathan Dinu](https://savrn.com/model-publishers/jonathandinu) Semantic segmentation model fine-tuned from nvidia/mit-b5 with CelebAMask-HQ for face parsing. For additional options, see the Transformers Segformer docs. Exhaustive list of labels can be extracted from config.json. Since p5.js uses an animation loop abstraction, we need to take care loading the model and making predictions. While the capabilities of computer vision models are impressive, they can also reinforce or exacerbate social biases. The CelebAMask-HQ dataset used for fine-tuning is large but not necessarily perfectly diverse or representative. Also, they are images of.... just celebrities. Open weights 85M parameters transformers [View model](https://savrn.com/models/face-parsing) Model · Image segmentation ### [mask2former-swin-tiny-coco-instance](https://savrn.com/models/mask2former-swin-tiny-coco-instance) [AI at Meta](https://savrn.com/model-publishers/facebook) Mask2Former model trained on COCO instance segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)… Open weights other 47M parameters transformers [View model](https://savrn.com/models/mask2former-swin-tiny-coco-instance) Model · Image segmentation ### [BiRefNet_lite](https://savrn.com/models/birefnet-lite) [Peng Zheng](https://savrn.com/model-publishers/zhengpeng7) This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Single Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: + Inference and evaluation of your given weights: + Many thanks to @fal for their generous… Open weights mit 44M parameters birefnet [View model](https://savrn.com/models/birefnet-lite) ## AI at Meta [All models and datasets](https://savrn.com/model-publishers/facebook) ## Versions - [1b7ac418a0f3](https://savrn.com/models/mask2former-swin-small-coco-instance/versions/1b7ac418a0f3) · current 2026-09-18 ## Explore More - [All image segmentation models](https://savrn.com/models/tasks/image-segmentation) - [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 2026-10-20. - [AI at Meta website](https://ai.meta.com/resources/models-and-libraries/) - [Hugging Face record](https://huggingface.co/facebook/mask2former-swin-small-coco-instance) - [How the hub is built](https://savrn.com/model-hub/methodology)