Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image classification
by PyTorch Image Models timm/tf_efficientnetv2_s.in21k_ft_in1k
A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. Explore the dataset and runtime metrics of this model in timm model results.
What it takes to serve tf_efficientnetv2_s.in21k_ft_in1k (22M 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 | 0.0 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 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.
Twenty-two million parameters, five files, 173 MB on disk. This EfficientNet-v2 classifier labels images, and its memory need rounds to 0.1 GB at 16-bit and to zero at 8-bit and 4-bit; it fits beside anything. Our cheapest listed host, one MI300X with 192 GB, runs $1.85 per hour on demand, but nobody should rent that card for this model alone; put it on a card that is already busy and the question becomes throughput per dollar, not memory.
On the license side there is nothing to negotiate. Apache 2.0 allows commercial use, modification and redistribution, includes an express patent grant, and asks only that you keep the license and copyright notices and state significant changes. Before fine-tuning, check the lineage: trained on ImageNet-21k, fine-tuned on ImageNet-1k in TensorFlow by the paper authors, then ported to PyTorch by Ross Wightman, with the method in arXiv:2104.00298.
By PyTorch Image Models, published under apache-2.0, revision ea9abc143ea2.
A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnetv2_s.in21k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
5 files, 173.2 MB in total. The weights are 2 files totalling 173.2 MB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 86.5 MB | 6f1933fb6c0d |
| pytorch_model.bin | Weights | 86.7 MB | 40ed79ccf7aa |
| config.json | Configuration | 638 B | — |
| README.md | Documentation | 4.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
Released by PyTorch Image Models through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 173.2 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (22M parameters) plus a working margin. A long context needs more.
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.
Yes. tf_efficientnetv2_s.in21k_ft_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.
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. ResNet Strikes Back A1 recipe - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman. - How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 Explore the dataset and runtime metrics of this model in timm model results.
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 16 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 16 - lrschedulertype: cosine - numepochs: 20 - labelsmoothingfactor: 0.1 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1
A RegNetY-3.2GF image classification model. Trained on ImageNet-1k by Ross Wightman in timm. The timm RegNet implementation includes a number of enhancements not present in other implementations, including: stochastic depth gradient checkpointing layer-wise LR decay configurable output stride (dilation) configurable activation and norm layers option for a pre-activation bottleneck block used in RegNetV variant only known RegNetZ model definitions with pretrained weights Explore the dataset and runtime metrics of this model in timm model results. For the comparison summary below, the rain1k, ra3in1k, chin1k, sw, and lion tagged weights are trained in timm.
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. Based on ResNet Strikes Back A1 recipe Stronger dropout, stochastic depth, and RandAugment than paper A1 recipe - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. ResNet Strikes Back A1 recipe - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.