Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image classification
by PyTorch Image Models timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k
vit_tiny_patch16_224.augreg_in21k_ft_in1k is an open-weight model for image classification from PyTorch Image Models, released under Apache License 2.0. It has 6M parameters. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 190.3k downloads a month.
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?
What it takes to serve vit_tiny_patch16_224.augreg_in21k_ft_in1k (6M 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 | 0.0 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 Oct 16, 2026.
ViT Tiny is the smallest standard vision transformer, 6M parameters, trained on ImageNet-21K and fine-tuned on ImageNet-1K. It runs on phones and CPUs.
Apache 2.0 allows commercial use. It is useful as a fast baseline, a teacher-student target, or a classifier where latency matters more than accuracy. Test EdgeNeXt small as an alternative for edge devices.
By PyTorch Image Models, published under apache-2.0, revision 7d3afdd0cf93.
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.
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('vit_tiny_patch16_224.augreg_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, 45.8 MB in total. The weights are 2 files totalling 45.8 MB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 22.9 MB | fecf81b492bd |
| pytorch_model.bin | Weights | 22.9 MB | 765ebd32b9f2 |
| config.json | Configuration | 586 B | — |
| README.md | Documentation | 3.9 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 | 45.8 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 GB at 16-bit and 0 GB at 4-bit: the weights (6M 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. vit_tiny_patch16_224.augreg_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 DeiT image classification model. Trained on ImageNet-1k by paper authors. - Training data-efficient image transformers & distillation through attention: https://arxiv.org/abs/2012.12877 Explore the dataset and runtime metrics of this model in timm model results.
An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (USI as per Solving ImageNet).
A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below. RandAugment RA 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 Explore the dataset and runtime metrics of this model in timm model results.
A CSPNeXt image classification model. Pretrained on ImageNet-1k by OpenMMLab (RTMDet) and converted to timm format. Name disambiguation: This is the CSPNeXt backbone of RTMDet (OpenMMLab), as implemented in MMDetection. A separate paper, CSPNeXt: A new efficient token hybrid backbone (Chen et al., EAAI 2024, doi:10.1016/j.engappai.2024.107886), uses the same name for a different architecture. These weights do not implement that paper; please cite RTMDet (below) for this model. - https://github.com/open-mmlab/mmdetection/tree/main/configs/rtmdet/classification - https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnextrsbpretrain/cspnext-simagenet600e-ea671761.pth ImageNet-1k validation…
A MobileNet-v3 image classification model. Trained 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.
A MobileNet-V4 image classification model. Trained on ImageNet-1k by Ross Wightman. Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 paper with timm enhancements. NOTE: So far, these are the only known MNV4 weights. Official weights for Tensorflow models are unreleased. - MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518