wide_resnet50_2.racm_in1k by PyTorch Image Models

Runs On

What it takes to serve wide_resnet50_2.racm_in1k (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 (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.

SAVRN's Notes on wide_resnet50_2.racm_in1k

Two tenths of a gigabyte is the whole memory footprint at 16-bit, weights included at 0.1 GB, so for this 69 million parameter image classifier the hardware question is what else shares the card. The cheapest setup we price is one MI300X with 192 GB at $1.85 an hour on demand, which sits nearly idle under a single instance, so batch hard or co-locate. The checkpoint was trained on ImageNet-1k under the RandAugment RACM recipe, the B recipe from ResNet Strikes Back.

Apache 2.0 permits commercial use, modification and redistribution, provided the license and copyright notices stay attached and significant changes are stated, with a patent grant from contributors. Access is open, with 437,389 downloads a month and a last update on January 21, 2025; before committing, read the three papers behind it, arXiv:2110.00476, arXiv:1605.07146 and arXiv:1512.03385, because the recipe is what you are buying, not just the architecture.

SAVRN Research, 2026-09-18

Model Card

By PyTorch Image Models, published under apache-2.0, revision 30f73aceaaa1.

Model card for wide_resnet50_2.racm_in1k

A Wide-ResNet-B image classification model.

This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample

Trained on ImageNet-1k in timm using recipe template described below.

Recipe details: * RandAugment RACM recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back. * RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging * Step (exponential decay w/ staircase) LR schedule with warmup

Model Details

Model Type: Image classification / feature backbone
Model Stats:
Params (M): 68.9
GMACs: 11.4
Activations (M): 14.4
Image size: train = 224 x 224, test = 288 x 288
Papers:
ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
Wide Residual Networks: https://arxiv.org/abs/1605.07146
Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

Read the full model card (2,600 words)

Identity and Version

Repository: timm/wide_resnet50_2.racm_in1k
Publisher: PyTorch Image Models
Task: Image classification
Modality: Image
Library: timm
Parameters: 69M parameters
Languages: Not stated by the source
Revision: 30f73aceaaa1911830a9795b83ab1908dba18719
First published: 2023-04-05
Last updated: 2025-01-21

Files and Weights

5 files, 551.8 MB in total. The weights are 2 files totalling 551.7 MB in bin, safetensors.

Weights2 files · 551.7 MB

Configuration1 file · 730 B

Documentation1 file · 39.3 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	275.8 MB	03b71d65fb2c
pytorch_model.bin	Weights	275.9 MB	ffcad4ccf5c7
config.json	Configuration	730 B	—
README.md	Documentation	39.3 KB	—
.gitattributes	Repository	1.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 551.7 MB

Download from PyTorch Image Models

Released by PyTorch Image Models through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:1512.03385
Described by arXiv:1605.07146
Described by arXiv:2110.00476

Memory Requirements

Precision	Weights in memory
As published	551.7 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 wide_resnet50_2.racm_in1k

How much GPU memory does wide_resnet50_2.racm_in1k 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 wide_resnet50_2.racm_in1k 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 wide_resnet50_2.racm_in1k commercially?

Yes. wide_resnet50_2.racm_in1k 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.

Similar Models

Model · Image classification

nsfw_image_detection

Falcons.ai

The Fine-Tuned Vision Transformer (ViT) is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for image classification tasks. This specific model, named "google/vit-base-patch16-224-in21k," is pre-trained on a substantial collection of images in a supervised manner, leveraging the ImageNet-21k dataset. The images in the pre-training dataset are resized to a resolution of 224x224 pixels, making it suitable for a wide range of image recognition tasks. During the training phase, meticulous attention was given to hyperparameter settings to ensure optimal model performance. The model was fine-tuned with a judiciously chosen batch size of 16. This choice not…

Open weights apache-2.0 86M parameters transformers

View model

Model · Image classification

gender-classification

Rizvan Dwikifirdaus

Autogenerated by HuggingPics Create your own image classifier for anything by running the demo on Google Colab. Report any issues with the demo at the github repo.

Open weights 86M parameters transformers

View model

Model · Image classification

rorshark-vit-base

Chester Enright

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 5.0 - Transformers 4.36.0.dev0 - Pytorch 2.1.1+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0

Open weights apache-2.0 86M parameters transformers

View model

Model · Image classification

gender-classification-2

Rizvan Dwikifirdaus

Autogenerated by HuggingPics Create your own image classifier for anything by running the demo on Google Colab. Report any issues with the demo at the github repo.

Open weights 86M parameters transformers

View model

Model · Image classification

nsfw-classifier

Giacomo Arienti

In today's digital world, user-generated content is a double-edged sword. While it fosters creativity and engagement, it also opens the door to inappropriate or illegal content being shared. Our NSFW Image Classifier is specifically designed to identify and filter out explicit images, including pornography, hentai, and sexually suggestive content, ensuring your platform remains safe, secure, and legally compliant. With more than 2M downloads, our NSFW Image Classifier has become the go-to solution for platforms looking to maintain a clean and safe environment for their users. Many developers and companies have already chosen our solution to protect their communities—will you be next? 1.…

Open weights cc-by-nc-nd-4.0 86M parameters transformers

View model

Model · Image classification

fairface_age_image_detection

Dmytro Iakubovskyi

Detects age group with about 59% accuracy based on an image. See https://www.kaggle.com/code/dima806/age-group-image-classification-vit for details.

Open weights apache-2.0 86M parameters transformers

View model