Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image feature extraction

vit_small_patch14_dinov2.lvd142m

by PyTorch Image Models timm/vit_small_patch14_dinov2.lvd142m

vit_small_patch14_dinov2.lvd142m is an open-weight model for image feature extraction from PyTorch Image Models, released under Apache License 2.0. It has 22M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 2.1M downloads a month.

A Vision Transformer (ViT) image feature model. Pretrained on LVD-142M with self-supervised DINOv2 method.

Parameters22M
Context—
Weights176.5 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.1M

Runs On

What it takes to serve vit_small_patch14_dinov2.lvd142m (22M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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 Oct 16, 2026.

vit_small_patch14_dinov2.lvd142m on every accelerator the SAVRN Index prices, at every precision

SAVRN's Notes on vit_small_patch14_dinov2.lvd142m

22M parameters of self-supervised DINOv2 features, pretrained on LVD-142M and published at 176.5 MB. The Runs On table rounds everything below 0.1 GB — this is an embedding extractor that rides in the spare memory of any serving GPU, at 0.1 GB even at 16-bit. The cheapest card we price, an MI300X at $1.85 an hour, is wildly unnecessary; the number that matters is encoder throughput per dollar on your own fleet.

Apache 2.0, no gate, single-file weights. Use it when you need transferable image features for retrieval, clustering or downstream probing; skip it if you need labels out of the box — the timm classification entries exist for that. With 1.4M downloads a month, most teams treat DINOv2 small as infrastructure, and that is the right mental model: boring, dependable, and effectively free to operate next to a real workload.

SAVRN Research

Model Card

By PyTorch Image Models, published under apache-2.0, revision 4610ca143709.

Model card for vit_small_patch14_dinov2.lvd142m

A Vision Transformer (ViT) image feature model. Pretrained on LVD-142M with self-supervised DINOv2 method.

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
  • Params (M): 22.1
  • GMACs: 46.8
  • Activations (M): 198.8
  • Image size: 518 x 518
  • Papers:
  • DINOv2: Learning Robust Visual Features without Supervision: https://arxiv.org/abs/2304.07193
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
  • Original: https://github.com/facebookresearch/dinov2
  • Pretrain Dataset: LVD-142M

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_small_patch14_dinov2.lvd142m', 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 (399 words)

Identity and Version

Repository
timm/vit_small_patch14_dinov2.lvd142m
Publisher
PyTorch Image Models
Task
Image feature extraction
Modality
Other
Library
timm
Parameters
22M parameters
Languages
Not stated by the source
Revision
4610ca143709d58a633b6397a74412c2c3842454
First published
2023-05-09
Last updated
2025-01-21

Files and Weights

5 files, 176.5 MB in total. The weights are 2 files totalling 176.5 MB in bin, safetensors.

Weights2 files · 176.5 MB
Configuration1 file · 615 B
Documentation1 file · 4.0 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights88.2 MB 04d27f3400d0
pytorch_model.binWeights88.3 MB 120606d7ac09
config.jsonConfiguration615 B —
README.mdDocumentation4.0 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
176.5 MB
Download from PyTorch Image Models

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

Built From

Memory Requirements

PrecisionWeights in memory
As published176.5 MB
16-bit0.0 GB
8-bit0.0 GB
4-bit0.0 GB

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

Compare vit_small_patch14_dinov2.lvd142m

Questions About vit_small_patch14_dinov2.lvd142m

How much GPU memory does vit_small_patch14_dinov2.lvd142m need?

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.

What is the cheapest GPU to run vit_small_patch14_dinov2.lvd142m 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_small_patch14_dinov2.lvd142m commercially?

Yes. vit_small_patch14_dinov2.lvd142m 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 feature extraction

dinov2-small

AI at Meta

Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features without Supervision by Oquab et al. and first released in this repository. Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One…

Open weights apache-2.0 22M parameters transformers
View model

Model · Image feature extraction

clip-vitb-mini-distilled

AbstractPhila

An 8.66M-parameter ViT image encoder (10.0% of a CLIP-B/16 image tower) producing 512-d embeddings compatible with the text tower. The primary checkpoint was distilled on CC12M (10,968,539 images) against the generalized-Procrustes consensus of five CLIP teachers — never against the deployment teacher — and carries a frozen 512×512 rotation that maps its outputs into the deployment frame, where it outperforms the student distilled directly against that teacher on every task gauge, both seeds (full tables below). The rotation is applied by default (config.applyrotation); pass applyrotation=False to getimagefeatures for the raw consensus-frame embedding. Weights are safetensors; the modeling…

Open weights apache-2.0 9M parameters transformers
View model

Model · Image feature extraction

I-JEPA-Agro

Junior R F Junior

Projeto completo de triagem visual de anomalias em folhas de soja usando como extrator de representações e HeraclitusDB como banco de eventos e vetores. 1. lê um manifesto com fazenda, talhão, safra e cultivar; 2. executa o I-JEPA ViT-G/16 localmente; 3. aplica média aos patch tokens e normalização L2; 4. persiste cada imagem e seu embedding euclidiano no HeraclitusDB; 5. cria um artefato local para avaliação offline; 6. treina uma sonda linear; 7. busca imagens visualmente semelhantes; 8. oferece busca por uma API FastAPI. - Python 3.11+; - HeraclitusDB ativo em 127.0.0.1:7474; - vários GB livres para o checkpoint; - RAM suficiente para um modelo com aproximadamente 1B parâmetros; - GPU é…

Open weights mit transformers
View model

Model · Image feature extraction

IM-Animation-Motion-Encoder

Fynn

IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation This release contains the final locally retained TiTok-based motion encoder implementation and an exported checkpoint. It provides frame-level motion tokens; it does not include the full animation generator or retargeting network. Code and project videos are available in the linked GitHub repository. The encoder was verified with PyTorch 2.7.1 on CPU using the exported BF16 weights. The weight file is 607,017,208 bytes (approximately 579 MiB). Its SHA256 and provenance are in checkpointinfo.json. frames must be RGB, normalized to [0, 1], with shape [N, 3, 256, 256]. The training preprocessing pads…

Open weights apache-2.0
View model

Model · Image feature extraction

RK182X-VIT-siglip2-so400m-patch14-384

RKNNAI

本仓库提供由 google/siglip2-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip2-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip2-so400m-patch14-384 - 源模型：google/siglip2-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

Open weights apache-2.0
View model

Model · Image feature extraction

RK182X-VIT-siglip-so400m-patch14-384

RKNNAI

本仓库提供由 google/siglip-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip-so400m-patch14-384 - 源模型：google/siglip-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

Open weights apache-2.0
View model