# beitv2_base_patch16_224.in1k_ft_in22k by PyTorch Image Models
Source: https://savrn.com/models/beitv2-base-patch16-224-in1k-ft-in22k
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve beitv2_base_patch16_224.in1k_ft_in22k (103M 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 | 0.2 GB | 0.2 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 | 0.1 GB | 0.1 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 | 0.1 GB | 0.1 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.

[beitv2_base_patch16_224.in1k_ft_in22k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/beitv2-base-patch16-224-in1k-ft-in22k/gpus)

## Model Card

By PyTorch Image Models, published under apache-2.0, revision db3a37523700.

### Model card for beitv2_base_patch16_224.in1k_ft_in22k

A BEiT-v2 image classification model. Trained on ImageNet-1k with self-supervised masked image modelling (MIM) using a VQ-KD encoder as a visual tokenizer (via OpenAI CLIP B/16 teacher). Fine-tuned on ImageNet-22k.

### Model Details

- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 102.6
- GMACs: 17.6
- Activations (M): 23.9
- Image size: 224 x 224
- Papers:
- BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers: https://arxiv.org/abs/2208.06366
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- Dataset: ImageNet-22k
- Original: https://github.com/microsoft/unilm/tree/master/beit2

### 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('beitv2_base_patch16_224.in1k_ft_in22k', 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 (356 words)](https://savrn.com/models/beitv2-base-patch16-224-in1k-ft-in22k/card)

## Identity and Version

Repository

timm/beitv2_base_patch16_224.in1k_ft_in22k

Publisher

PyTorch Image Models

Task

Image classification

Modality

Image

Library

timm

Parameters

103M parameters

Languages

Not stated by the source

Revision

db3a37523700d6507b4973ce0898d55216530c68

First published

2022-12-23

Last updated

2025-01-21

## Files and Weights

5 files, 828.0 MB in total. The weights are 2 files totalling 828.0 MB in bin, safetensors.

Weights2 files · 828.0 MB

Configuration1 file · 595 B

Documentation1 file · 3.8 KB

Repository1 file · 1.5 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 414.0 MB | 49c50015f6db |
| pytorch_model.bin | Weights | 414.0 MB | 53f69b90e0ad |
| config.json | Configuration | 595 B | — |
| README.md | Documentation | 3.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |

## License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

828.0 MB

[Download from PyTorch Image Models](https://huggingface.co/timm/beitv2_base_patch16_224.in1k_ft_in22k)

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:2208.06366
- Trained on (disclosed) imagenet-22k

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 828.0 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |

Weights only, from the published parameter count; the key-value cache and runtime add to this.

## Questions About beitv2_base_patch16_224.in1k_ft_in22k

### How much GPU memory does beitv2_base_patch16_224.in1k_ft_in22k need?

About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (103M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run beitv2_base_patch16_224.in1k_ft_in22k 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 beitv2_base_patch16_224.in1k_ft_in22k commercially?

Yes. beitv2_base_patch16_224.in1k_ft_in22k 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

### [vit_base_patch16_224.augreg_in21k](https://savrn.com/models/vit-base-patch16-224-augreg-in21k)

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

A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k (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.

Open weights apache-2.0 103M parameters timm

[View model](https://savrn.com/models/vit-base-patch16-224-augreg-in21k)

Model · Image classification

### [siglip2-x256-explicit-content](https://savrn.com/models/siglip2-x256-explicit-content)

[Prithiv Sakthi](https://savrn.com/model-publishers/prithivmlmods)

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features https://arxiv.org/pdf/2502.14786 The model classifies each image into one of the following content categories: This model is intended for applications such as

Open weights apache-2.0 93M parameters 64 tokens transformers

[View model](https://savrn.com/models/siglip2-x256-explicit-content)

Model · Image classification

### [Gender-Classifier-Mini](https://savrn.com/models/gender-classifier-mini)

[Prithiv Sakthi](https://savrn.com/model-publishers/prithivmlmods)

The model categorizes images into two classes: The Gender-Classifier-Mini model is designed to classify images into gender categories. Potential use cases include

Open weights apache-2.0 93M parameters 64 tokens transformers

[View model](https://savrn.com/models/gender-classifier-mini)

Model · Image classification

### [swin_base_patch4_window12_384.ms_in22k_ft_in1k](https://savrn.com/models/swin-base-patch4-window12-384-ms-in22k-ft-in1k)

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

A Swin Transformer image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results.

Open weights mit 91M parameters timm

[View model](https://savrn.com/models/swin-base-patch4-window12-384-ms-in22k-ft-in1k)

Model · Image classification

### [PlantDetect-V2-Preview](https://savrn.com/models/plantdetect-v2-preview)

[Thenukegun10x](https://savrn.com/model-publishers/thenukegun10x)

Built with DINOv3. This is the completed V2 mean-pooling model for 2,991 plant species from Western Australia. Supply one photo, or 2–4 distinct photos from the same plant observation. This release uses the epoch-12 EMA weights from the expanded-data BF16 training run. The CLI uses self-contained TorchScript graphs (encoder.ts and classifier.ts) and imports no project modules. FP32 model.safetensors is also included for research use. Optimizer state and training data are excluded. executorch/PlantDetect-WA-V2-INT8.pte is a W8A8 export of this mean-pooling checkpoint for CPU inference without PyTorch. It uses custom plantquant:: kernels (INT8 weights with per-output-channel FP32 scales, FP16…

Open weights other 115M parameters pytorch

[View model](https://savrn.com/models/plantdetect-v2-preview)

Model · Image classification

### [convnextv2-base-22k-384](https://savrn.com/models/convnextv2-base-22k-384)

[AI at Meta](https://savrn.com/model-publishers/facebook)

ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 384x384. It was introduced in the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo et al. and first released in this repository. Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to ConvNeXt. ConvNeXt V2 significantly improves the performance of pure ConvNets on various…

Open weights apache-2.0 89M parameters transformers

[View model](https://savrn.com/models/convnextv2-base-22k-384)

## PyTorch Image Models

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

## Versions

- [db3a37523700](https://savrn.com/models/beitv2-base-patch16-224-in1k-ft-in22k/versions/db3a37523700) · 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/beitv2_base_patch16_224.in1k_ft_in22k)
- [How the hub is built](https://savrn.com/model-hub/methodology)