# vit_tiny_patch16_224.augreg_in21k_ft_in1k by PyTorch Image Models
Source: https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

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](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 | 0.0 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 |
| 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.

[vit_tiny_patch16_224.augreg_in21k_ft_in1k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k/gpus)

## SAVRN's Notes on vit_tiny_patch16_224.augreg_in21k_ft_in1k

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.

SAVRN Research, 2026-09-18

## Model Card

By PyTorch Image Models, published under apache-2.0, revision 7d3afdd0cf93.

### Model card for vit_tiny_patch16_224.augreg_in21k_ft_in1k

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.

### Model Details

- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 5.7
- GMACs: 1.1
- Activations (M): 4.1
- Image size: 224 x 224
- Papers:
- 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
- Dataset: ImageNet-1k
- Pretrain Dataset: ImageNet-21k
- Original: https://github.com/google-research/vision_transformer

### Model Usage

#### Image Classification

```
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)
```

#### Image Embeddings

[Read the full model card (369 words)](https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k/card)

## Identity and Version

Repository

timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k

Publisher

PyTorch Image Models

Task

Image classification

Modality

Image

Library

timm

Parameters

6M parameters

Languages

Not stated by the source

Revision

7d3afdd0cf93ad84d986eb2d6bcc5812ebd0b106

First published

2022-12-22

Last updated

2025-01-21

## Files and Weights

5 files, 45.8 MB in total. The weights are 2 files totalling 45.8 MB in bin, safetensors.

Weights2 files · 45.8 MB

Configuration1 file · 586 B

Documentation1 file · 3.9 KB

Repository1 file · 1.5 KB

Every file

| 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 | — |

## License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

45.8 MB

[Download from PyTorch Image Models](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k)

Released by PyTorch Image Models through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0).

## Built From

- Described by [arXiv:2010.11929](https://savrn.com/papers/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale)
- Described by [arXiv:2106.10270](https://savrn.com/papers/how-to-train-your-vit-data-augmentation-and-regularization-in-vision-transformers)
- Trained on (disclosed) imagenet-1k
- Trained on (disclosed) imagenet-21k

## Memory Requirements

| 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.

## Questions About vit_tiny_patch16_224.augreg_in21k_ft_in1k

### How much GPU memory does vit_tiny_patch16_224.augreg_in21k_ft_in1k need?

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.

### What is the cheapest GPU to run vit_tiny_patch16_224.augreg_in21k_ft_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 vit_tiny_patch16_224.augreg_in21k_ft_in1k commercially?

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.

## Similar Models

Model · Image classification

### [deit_tiny_patch16_224.fb_in1k](https://savrn.com/models/deit-tiny-patch16-224-fb-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 6M parameters timm

[View model](https://savrn.com/models/deit-tiny-patch16-224-fb-in1k)

Model · Image classification

### [edgenext_small.usi_in1k](https://savrn.com/models/edgenext-small-usi-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

An EdgeNeXt image classification model. Trained on ImageNet-1k by paper authors using distillation (USI as per Solving ImageNet).

Open weights mit 6M parameters timm

[View model](https://savrn.com/models/edgenext-small-usi-in1k)

Model · Image classification

### [efficientnet_b0.ra_in1k](https://savrn.com/models/efficientnet-b0-ra-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 5M parameters timm

[View model](https://savrn.com/models/efficientnet-b0-ra-in1k)

Model · Image classification

### [cspnext_s.rsb_a1_in1k](https://savrn.com/models/cspnext-s-rsb-a1-in1k)

[Munehiro Kobayashi](https://savrn.com/model-publishers/munehiro-k)

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…

Open weights apache-2.0 5M parameters timm

[View model](https://savrn.com/models/cspnext-s-rsb-a1-in1k)

Model · Image classification

### [tf_mobilenetv3_large_minimal_100.in1k](https://savrn.com/models/tf-mobilenetv3-large-minimal-100-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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.

Open weights apache-2.0 4M parameters timm

[View model](https://savrn.com/models/tf-mobilenetv3-large-minimal-100-in1k)

Model · Image classification

### [mobilenetv4_conv_small.e2400_r224_in1k](https://savrn.com/models/mobilenetv4-conv-small-e2400-r224-in1k)

[PyTorch Image Models](https://savrn.com/model-publishers/timm)

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

Open weights apache-2.0 4M parameters timm

[View model](https://savrn.com/models/mobilenetv4-conv-small-e2400-r224-in1k)

## PyTorch Image Models

[All models and datasets](https://savrn.com/model-publishers/timm)

## Versions

- [7d3afdd0cf93](https://savrn.com/models/vit-tiny-patch16-224-augreg-in21k-ft-in1k/versions/7d3afdd0cf93) · current 2026-09-18

## Explore More

- [All image classification models](https://savrn.com/models/tasks/image-classification)
- [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0)
- [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.
- [PyTorch Image Models website](https://github.com/huggingface/pytorch-image-models)
- [Hugging Face record](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k)
- [How the hub is built](https://savrn.com/model-hub/methodology)