upernet-convnext-tiny by OpenMMLab: Open-Weight Model

Runs On

What it takes to serve upernet-convnext-tiny (60M 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 (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.0 GB	0.0 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x 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, read Sep 18, 2026.

Model Card

By OpenMMLab, published under mit, revision 876ffc56b819.

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…

Read OpenMMLab's full model card

UperNet, ConvNeXt tiny-sized backbone

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.

Model description

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 semantic label per pixel.

Intended uses & limitations

You can use the raw model for semantic segmentation. See the model hub to look for fine-tuned versions (with various backbones) on a task that interests you.

How to use

For code examples, we refer to the documentation.

Configuration

Architecture: UperNetForSemanticSegmentation
Hidden size: 512
Stored precision: float32
Model type: upernet

Identity and Version

Repository: openmmlab/upernet-convnext-tiny
Publisher: OpenMMLab
Task: Image segmentation
Modality: Image
Library: transformers
Parameters: 60M parameters
Languages: en
Revision: 876ffc56b819a829448f7e81e9f8606deef6fb65
First published: 2023-01-13
Last updated: 2023-04-24

Files and Weights

6 files, 482.2 MB in total. The weights are 2 files totalling 482.2 MB in bin, safetensors.

Weights2 files · 482.2 MB

Configuration2 files · 9.1 KB

Documentation1 file · 1.6 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	241.1 MB	cd55b1d36c66
pytorch_model.bin	Weights	241.1 MB	4f5d3b46a4fc
config.json	Configuration	8.8 KB	—
preprocessor_config.json	Configuration	372 B	—
README.md	Documentation	1.6 KB	—
.gitattributes	Repository	1.5 KB	—

License and Download

License: mit
Access: Open weights, no gate
Download size: 482.2 MB

Download from OpenMMLab

Released by OpenMMLab through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:1807.10221
Described by arXiv:2201.03545

Memory Requirements

Precision	Weights in memory
As published	482.2 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 upernet-convnext-tiny

How much GPU memory does upernet-convnext-tiny need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (60M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run upernet-convnext-tiny 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 upernet-convnext-tiny commercially?

Yes. upernet-convnext-tiny is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Image segmentation

fashn-human-parser

FASHN

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

Model · Image segmentation

mask2former-swin-small-coco-instance

AI at Meta

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)…

Open weights other 69M parameters transformers

View model

Model · Image segmentation

mask2former-swin-small-ade-semantic

AI at Meta

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

Model · Image segmentation

mask2former-swin-tiny-coco-instance

AI at Meta

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

Model · Image segmentation

BiRefNet_lite

Peng Zheng

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

Model · Image segmentation

RMBG-1.4

BRIA AI

RMBG v1.4 is our state-of-the-art background removal model, designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use cases powering enterprise content creation at scale. The accuracy, efficiency, and versatility currently rival leading source-available models. It is ideal where content safety, legally licensed datasets, and bias mitigation are paramount. Developed by BRIA AI, RMBG v1.4 is available as a source-available model for non-commercial use. To purchase a…

Open weights other 44M parameters transformers

View model