# Vision Transformer (ViT)

**Category:** ViT · **Code:**
[`timm/models/vision_transformer.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py)
· **Architectures:** 157 · **Pretrained weights:** 302 (96 with ImageNet-1k results)

The Vision Transformer (ViT) splits an image into fixed size patches, linearly embeds them and processes the resulting
token sequence with a standard Transformer encoder. This module holds the `VisionTransformer` class and the weights for
the original ViT, the "How to train your ViT?" (AugReg) and FlexiViT models, and many image-text (CLIP, SigLIP) and
self-supervised pretrained image towers that share the architecture.

## Papers

* [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929)
* [How to train your ViT? Data, Augmentation, and Regularization in Vision
  Transformers](https://arxiv.org/abs/2106.10270)
* [FlexiViT: One Model for All Patch Sizes](https://arxiv.org/abs/2212.08013)
* [Scaling Vision Transformers](https://arxiv.org/abs/2106.04560)
* [Three things everyone should know about Vision Transformers](https://arxiv.org/abs/2203.09795)
* [Scaling Vision Transformers to 22 Billion Parameters](https://arxiv.org/abs/2302.05442)
* [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://arxiv.org/abs/2305.13035)
* [Vision Transformers Need Registers](https://arxiv.org/abs/2309.16588)
* [Differential Transformer](https://arxiv.org/abs/2410.05258)
* [When Vision Transformers Outperform ResNets without Pre-training or Strong Data
  Augmentations](https://arxiv.org/abs/2106.01548)
* [ImageNet-21K Pretraining for the Masses](https://arxiv.org/abs/2104.10972)
* [Emerging Properties in Self-Supervised Vision Transformers](https://arxiv.org/abs/2104.14294)
* [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193)
* [Masked Autoencoders Are Scalable Vision Learners](https://arxiv.org/abs/2111.06377)
* [Self-Supervised Learning from Images with a Joint-Embedding Predictive
  Architecture](https://arxiv.org/abs/2301.08243)
* [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://arxiv.org/abs/2211.07636)
* [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language
  Tasks](https://arxiv.org/abs/2208.10442)
* [Multimodal Autoregressive Pre-training of Large Vision Encoders](https://arxiv.org/abs/2411.14402)
* [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/abs/2103.00020)
* [Reproducible scaling laws for contrastive language-image learning](https://arxiv.org/abs/2212.07143)
* [DataComp: In search of the next generation of multimodal datasets](https://arxiv.org/abs/2304.14108)
* [Data Filtering Networks](https://arxiv.org/abs/2309.17425)
* [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671)
* [Altogether: Image Captioning via Re-aligning Alt-text](https://arxiv.org/abs/2410.17251)
* [Meta CLIP 2: A Worldwide Scaling Recipe](https://arxiv.org/abs/2507.22062)
* [TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance](https://arxiv.org/abs/2309.12314)
* [MobileCLIP2: Improving Multi-Modal Reinforced Training](https://arxiv.org/abs/2508.20691)
* [Sigmoid Loss for Language Image Pre-Training](https://arxiv.org/abs/2303.15343)
* [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense
  Features](https://arxiv.org/abs/2502.14786)
* [PaliGemma: A versatile 3B VLM for transfer](https://arxiv.org/abs/2407.07726)
* [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://arxiv.org/abs/2412.03555)
* [TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment](https://arxiv.org/abs/2604.12012)
* [Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90%
  Performance](https://arxiv.org/abs/2410.16261)
* [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time
  Scaling](https://arxiv.org/abs/2412.05271)

## Usage

See the [Quickstart](../quickstart) for loading pretrained weights, image preprocessing and fine-tuning, and [Feature
Extraction](../feature_extraction) for using the models as backbones.

```py
>>> import timm
>>> model = timm.create_model('vit_base_patch16_224.augreg2_in21k_ft_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `VisionTransformer` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 16, 16, 16) |
| [`forward_intermediates()`](../model_api#intermediate-features) | ✓ |
| [`prune_intermediate_layers()`](../model_api#intermediate-features) | ✓ |
| [Any input size, no changes needed](../model_api#input-size) | ✗ |
| [`set_input_size()`](../model_api#input-size) | ✓ |
| [`dynamic_img_size=True`](../model_api#input-size) | ✓ |
| [`set_grad_checkpointing()`](../model_api#training-hooks) | ✓ |
| [Layer-wise LR decay (`group_matcher()`)](../model_api#training-hooks) | ✓ |
| [`reset_classifier()`](../model_api#classifier) | ✓ |

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input
size). Checked by running each feature on a randomly initialized model (`VisionTransformer` with `vit_tiny_patch16_224`
at 224), other architectures of the same class are expected to behave the same. See the [Model API](../model_api) page
for details.

## Architectures

| Architecture | Params (M) | GMACs | Input size | Pretrained weights |
|---|---:|---:|---:|---:|
| `aimv2_1b_patch14_224` | 1234.96 | 322.43 | 224 | 1 |
| `aimv2_1b_patch14_336` | 1235.61 | 743.59 | 336 | 1 |
| `aimv2_1b_patch14_448` | 1236.53 | 1367.03 | 448 | 1 |
| `aimv2_3b_patch14_224` | 2720.66 | 705.91 | 224 | 1 |
| `aimv2_3b_patch14_336` | 2721.64 | 1615.48 | 336 | 1 |
| `aimv2_3b_patch14_448` | 2723.02 | 2939.61 | 448 | 1 |
| `aimv2_huge_patch14_224` | 680.85 | 179.01 | 224 | 1 |
| `aimv2_huge_patch14_336` | 681.34 | 416.36 | 336 | 1 |
| `aimv2_huge_patch14_448` | 682.03 | 774.02 | 448 | 1 |
| `aimv2_large_patch14_224` | 309.20 | 82.30 | 224 | 2 |
| `aimv2_large_patch14_336` | 309.53 | 194.22 | 336 | 2 |
| `aimv2_large_patch14_448` | 309.98 | 367.84 | 448 | 1 |
| `beit3_base_patch16_224` | 86.66 | 17.63 | 224 | 4 |
| `beit3_giant_patch14_224` | 1013.22 | 267.56 | 224 | 0 |
| `beit3_giant_patch14_336` | 1013.67 | 621.52 | 336 | 0 |
| `beit3_large_patch16_224` | 304.57 | 61.72 | 224 | 4 |
| `eva_large_patch14_196` | 304.14 | 61.57 | 196 | 2 |
| `eva_large_patch14_336` | 304.53 | 191.10 | 336 | 2 |
| `flexivit_base` | 86.59 | 20.29 | 240 | 7 |
| `flexivit_large` | 304.36 | 70.99 | 240 | 3 |
| `flexivit_small` | 22.06 | 5.35 | 240 | 3 |
| `test_vit` | 0.37 | 0.04 | 160 | 1 |
| `test_vit2` | 0.46 | 0.05 | 160 | 1 |
| `test_vit3` | 0.93 | 0.09 | 160 | 1 |
| `test_vit4` | 1.02 | 0.11 | 160 | 0 |
| `vit_base_patch8_224` | 86.58 | 78.22 | 224 | 4 |
| `vit_base_patch14_dinov2` | 86.58 | 151.71 | 518 | 1 |
| `vit_base_patch14_reg1_tipsv2` | 86.31 | - | 448 | 1 |
| `vit_base_patch14_reg4_dinov2` | 86.58 | 152.25 | 518 | 1 |
| `vit_base_patch16_18x2_224` | 256.73 | 52.51 | 224 | 0 |
| `vit_base_patch16_224` | 86.57 | 17.58 | 224 | 9 |
| `vit_base_patch16_224_miil` | 94.40 | 17.59 | 224 | 2 |
| `vit_base_patch16_384` | 86.86 | 55.54 | 384 | 3 |
| `vit_base_patch16_clip_224` | 86.57 | 17.58 | 224 | 13 |
| `vit_base_patch16_clip_384` | 86.86 | 55.54 | 384 | 4 |
| `vit_base_patch16_clip_quickgelu_224` | 86.19 | 17.58 | 224 | 3 |
| `vit_base_patch16_gap_224` | 86.57 | 17.49 | 224 | 0 |
| `vit_base_patch16_plus_240` | 117.56 | 27.41 | 240 | 0 |
| `vit_base_patch16_plus_clip_240` | 117.21 | 27.41 | 240 | 1 |
| `vit_base_patch16_reg4_gap_256` | 86.62 | 23.50 | 256 | 0 |
| `vit_base_patch16_rpn_224` | 86.54 | 17.49 | 224 | 1 |
| `vit_base_patch16_siglip_224` | 92.88 | 17.73 | 224 | 2 |
| `vit_base_patch16_siglip_256` | 92.93 | 23.44 | 256 | 3 |
| `vit_base_patch16_siglip_384` | 93.18 | 56.12 | 384 | 2 |
| `vit_base_patch16_siglip_512` | 93.52 | 108.22 | 512 | 2 |
| `vit_base_patch16_siglip_gap_224` | 85.80 | 17.49 | 224 | 2 |
| `vit_base_patch16_siglip_gap_256` | 85.84 | 23.13 | 256 | 3 |
| `vit_base_patch16_siglip_gap_384` | 86.09 | 55.43 | 384 | 2 |
| `vit_base_patch16_siglip_gap_512` | 86.43 | 107.00 | 512 | 2 |
| `vit_base_patch16_xp_224` | 86.51 | 17.56 | 224 | 0 |
| `vit_base_patch32_224` | 88.22 | 4.41 | 224 | 5 |
| `vit_base_patch32_384` | 88.30 | 13.06 | 384 | 2 |
| `vit_base_patch32_clip_224` | 88.22 | 4.41 | 224 | 9 |
| `vit_base_patch32_clip_256` | 87.86 | 5.76 | 256 | 1 |
| `vit_base_patch32_clip_384` | 88.30 | 13.06 | 384 | 2 |
| `vit_base_patch32_clip_448` | 88.34 | 17.93 | 448 | 1 |
| `vit_base_patch32_clip_quickgelu_224` | 87.85 | 4.41 | 224 | 4 |
| `vit_base_patch32_plus_256` | 119.48 | 7.79 | 256 | 0 |
| `vit_base_patch32_siglip_256` | 94.55 | 5.75 | 256 | 1 |
| `vit_base_patch32_siglip_gap_256` | 87.47 | 5.67 | 256 | 1 |
| `vit_betwixt_patch16_gap_256` | 60.37 | 16.25 | 256 | 0 |
| `vit_betwixt_patch16_reg1_gap_256` | 60.40 | 16.32 | 256 | 1 |
| `vit_betwixt_patch16_reg4_gap_256` | 60.40 | 16.52 | 256 | 5 |
| `vit_betwixt_patch16_reg4_gap_384` | 60.60 | 39.71 | 384 | 1 |
| `vit_betwixt_patch32_clip_224` | 61.41 | 3.09 | 224 | 1 |
| `vit_dlittle_patch16_reg1_gap_256` | 22.52 | 6.27 | 256 | 1 |
| `vit_dpwee_patch16_reg1_gap_256` | 15.25 | 4.37 | 256 | 2 |
| `vit_dwee_patch16_reg1_gap_256` | 13.43 | 3.83 | 256 | 2 |
| `vit_giant_patch14_224` | 1012.61 | 267.18 | 224 | 0 |
| `vit_giant_patch14_clip_224` | 1012.65 | 267.18 | 224 | 1 |
| `vit_giant_patch14_dinov2` | 1136.48 | 1784.20 | 518 | 1 |
| `vit_giant_patch14_reg1_tipsv2` | 1135.95 | - | 448 | 1 |
| `vit_giant_patch14_reg4_dinov2` | 1136.48 | 1790.08 | 518 | 1 |
| `vit_giant_patch16_gap_224` | 1011.37 | 202.46 | 224 | 1 |
| `vit_giantopt_patch16_siglip_256` | 1163.17 | 299.66 | 256 | 1 |
| `vit_giantopt_patch16_siglip_384` | 1163.66 | 696.85 | 384 | 1 |
| `vit_giantopt_patch16_siglip_gap_256` | 1134.84 | 298.42 | 256 | 1 |
| `vit_giantopt_patch16_siglip_gap_384` | 1135.33 | 694.10 | 384 | 1 |
| `vit_gigantic_patch14_224` | 1844.44 | 483.95 | 224 | 0 |
| `vit_gigantic_patch14_clip_224` | 1844.91 | 483.96 | 224 | 3 |
| `vit_gigantic_patch14_clip_378` | 1845.70 | 1429.82 | 378 | 1 |
| `vit_gigantic_patch14_clip_quickgelu_224` | 1844.91 | 483.96 | 224 | 1 |
| `vit_huge_patch14_224` | 630.76 | 167.40 | 224 | 2 |
| `vit_huge_patch14_clip_224` | 632.05 | 167.40 | 224 | 8 |
| `vit_huge_patch14_clip_336` | 632.46 | 390.97 | 336 | 1 |
| `vit_huge_patch14_clip_378` | 632.68 | 503.79 | 378 | 2 |
| `vit_huge_patch14_clip_quickgelu_224` | 632.08 | 167.40 | 224 | 3 |
| `vit_huge_patch14_clip_quickgelu_378` | 632.68 | 503.79 | 378 | 1 |
| `vit_huge_patch14_gap_224` | 630.76 | 166.73 | 224 | 2 |
| `vit_huge_patch14_xp_224` | 631.80 | 167.30 | 224 | 0 |
| `vit_huge_patch16_gap_448` | 631.67 | 544.70 | 448 | 1 |
| `vit_intern300m_patch14_448` | 304.01 | 362.05 | 448 | 2 |
| `vit_large_patch14_224` | 304.20 | 81.08 | 224 | 0 |
| `vit_large_patch14_clip_224` | 304.20 | 81.08 | 224 | 15 |
| `vit_large_patch14_clip_336` | 304.53 | 191.11 | 336 | 4 |
| `vit_large_patch14_clip_quickgelu_224` | 303.97 | 81.08 | 224 | 4 |
| `vit_large_patch14_clip_quickgelu_336` | 304.29 | 191.11 | 336 | 1 |
| `vit_large_patch14_dinov2` | 304.37 | 507.15 | 518 | 1 |
| `vit_large_patch14_reg1_tipsv2` | 304.01 | - | 448 | 1 |
| `vit_large_patch14_reg4_dinov2` | 304.37 | 508.90 | 518 | 1 |
| `vit_large_patch14_xp_224` | 304.06 | 81.01 | 224 | 0 |
| `vit_large_patch16_224` | 304.33 | 61.60 | 224 | 4 |
| `vit_large_patch16_384` | 304.72 | 191.21 | 384 | 1 |
| `vit_large_patch16_siglip_256` | 315.96 | 81.34 | 256 | 2 |
| `vit_large_patch16_siglip_384` | 316.28 | 192.07 | 384 | 2 |
| `vit_large_patch16_siglip_512` | 316.74 | 364.00 | 512 | 1 |
| `vit_large_patch16_siglip_gap_256` | 303.36 | 80.80 | 256 | 2 |
| `vit_large_patch16_siglip_gap_384` | 303.69 | 190.85 | 384 | 2 |
| `vit_large_patch16_siglip_gap_512` | 304.15 | 361.84 | 512 | 1 |
| `vit_large_patch32_224` | 305.51 | 15.39 | 224 | 1 |
| `vit_large_patch32_384` | 306.63 | 45.31 | 384 | 1 |
| `vit_little_patch16_reg1_gap_256` | 22.52 | 6.27 | 256 | 2 |
| `vit_little_patch16_reg4_gap_256` | 22.52 | 6.35 | 256 | 1 |
| `vit_medium_patch16_clip_224` | 38.59 | 8.00 | 224 | 1 |
| `vit_medium_patch16_gap_240` | 44.40 | 9.22 | 240 | 1 |
| `vit_medium_patch16_gap_256` | 38.86 | 10.59 | 256 | 1 |
| `vit_medium_patch16_gap_384` | 39.03 | 26.08 | 384 | 1 |
| `vit_medium_patch16_reg1_gap_256` | 38.88 | 10.63 | 256 | 1 |
| `vit_medium_patch16_reg4_gap_256` | 38.88 | 10.76 | 256 | 3 |
| `vit_medium_patch32_clip_224` | 39.69 | 2.00 | 224 | 1 |
| `vit_mediumd_patch16_reg4_gap_256` | 64.11 | 17.87 | 256 | 4 |
| `vit_mediumd_patch16_reg4_gap_384` | 64.27 | 43.67 | 384 | 1 |
| `vit_pwee_patch16_reg1_gap_256` | 15.25 | 4.37 | 256 | 1 |
| `vit_small_patch8_224` | 21.67 | 22.44 | 224 | 1 |
| `vit_small_patch14_dinov2` | 22.06 | 46.76 | 518 | 1 |
| `vit_small_patch14_reg4_dinov2` | 22.06 | 46.95 | 518 | 1 |
| `vit_small_patch16_18x2_224` | 64.67 | 13.71 | 224 | 0 |
| `vit_small_patch16_36x1_224` | 64.67 | 13.71 | 224 | 0 |
| `vit_small_patch16_224` | 22.05 | 4.61 | 224 | 4 |
| `vit_small_patch16_384` | 22.20 | 15.52 | 384 | 2 |
| `vit_small_patch32_224` | 22.88 | 1.15 | 224 | 2 |
| `vit_small_patch32_384` | 22.92 | 3.45 | 384 | 1 |
| `vit_so150m2_patch16_reg1_gap_256` | 136.06 | 37.00 | 256 | 2 |
| `vit_so150m2_patch16_reg1_gap_384` | 136.33 | 89.53 | 384 | 1 |
| `vit_so150m2_patch16_reg1_gap_448` | 136.50 | 127.51 | 448 | 1 |
| `vit_so150m_patch16_reg4_gap_256` | 134.13 | 36.75 | 256 | 2 |
| `vit_so150m_patch16_reg4_gap_384` | 134.42 | 87.97 | 384 | 1 |
| `vit_so150m_patch16_reg4_map_256` | 141.48 | 37.17 | 256 | 0 |
| `vit_so400m_patch14_reg1_tipsv2` | 413.39 | - | 448 | 1 |
| `vit_so400m_patch14_siglip_224` | 427.68 | 110.26 | 224 | 2 |
| `vit_so400m_patch14_siglip_378` | 428.23 | 335.40 | 378 | 3 |
| `vit_so400m_patch14_siglip_384` | 428.23 | 335.40 | 384 | 1 |
| `vit_so400m_patch14_siglip_gap_224` | 412.44 | 109.57 | 224 | 6 |
| `vit_so400m_patch14_siglip_gap_378` | 412.99 | 333.46 | 378 | 3 |
| `vit_so400m_patch14_siglip_gap_384` | 412.99 | 333.46 | 384 | 1 |
| `vit_so400m_patch14_siglip_gap_448` | 413.33 | 487.18 | 448 | 8 |
| `vit_so400m_patch14_siglip_gap_896` | 416.87 | 2731.49 | 896 | 5 |
| `vit_so400m_patch16_siglip_256` | 427.89 | 110.31 | 256 | 2 |
| `vit_so400m_patch16_siglip_384` | 428.26 | 259.65 | 384 | 1 |
| `vit_so400m_patch16_siglip_512` | 428.77 | 490.13 | 512 | 1 |
| `vit_so400m_patch16_siglip_gap_256` | 412.65 | 109.62 | 256 | 2 |
| `vit_so400m_patch16_siglip_gap_384` | 413.02 | 258.11 | 384 | 1 |
| `vit_so400m_patch16_siglip_gap_512` | 413.53 | 487.40 | 512 | 1 |
| `vit_tiny_patch16_224` | 5.72 | 1.26 | 224 | 2 |
| `vit_tiny_patch16_384` | 5.79 | 4.70 | 384 | 1 |
| `vit_wee_patch16_reg1_gap_256` | 13.42 | 3.83 | 256 | 1 |
| `vit_xsmall_patch16_clip_224` | 8.28 | 1.79 | 224 | 1 |

GMACs and parameter counts are for the default input size and classifier of each architecture, from the [benchmark
results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Pretrained weights

Top-1 is ImageNet-1k validation accuracy from
[`results-imagenet.csv`](https://github.com/huggingface/pytorch-image-models/blob/main/results/results-imagenet.csv) at
the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the
size of the pretrained classifier, none for weights without one.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than
`timm`, else the first part of the pretrained tag (`architecture.tag`). Sources with a single weight are listed under
other.

### `v2` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_siglip_224.v2_webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_224.v2_webli) |
| `vit_base_patch16_siglip_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_256.v2_webli) |
| `vit_base_patch16_siglip_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_384.v2_webli) |
| `vit_base_patch16_siglip_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_512.v2_webli) |
| `vit_base_patch16_siglip_gap_224.v2_webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_224.v2_webli) |
| `vit_base_patch16_siglip_gap_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_256.v2_webli) |
| `vit_base_patch16_siglip_gap_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_384.v2_webli) |
| `vit_base_patch16_siglip_gap_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_512.v2_webli) |
| `vit_base_patch32_siglip_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_siglip_256.v2_webli) |
| `vit_base_patch32_siglip_gap_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_siglip_gap_256.v2_webli) |
| `vit_giantopt_patch16_siglip_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giantopt_patch16_siglip_256.v2_webli) |
| `vit_giantopt_patch16_siglip_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giantopt_patch16_siglip_384.v2_webli) |
| `vit_giantopt_patch16_siglip_gap_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giantopt_patch16_siglip_gap_256.v2_webli) |
| `vit_giantopt_patch16_siglip_gap_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giantopt_patch16_siglip_gap_384.v2_webli) |
| `vit_large_patch16_siglip_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_256.v2_webli) |
| `vit_large_patch16_siglip_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_384.v2_webli) |
| `vit_large_patch16_siglip_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_512.v2_webli) |
| `vit_large_patch16_siglip_gap_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_gap_256.v2_webli) |
| `vit_large_patch16_siglip_gap_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_gap_384.v2_webli) |
| `vit_large_patch16_siglip_gap_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_gap_512.v2_webli) |
| `vit_so400m_patch14_siglip_224.v2_webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_224.v2_webli) |
| `vit_so400m_patch14_siglip_378.v2_webli` | 378 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_378.v2_webli) |
| `vit_so400m_patch14_siglip_gap_224.v2_webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.v2_webli) |
| `vit_so400m_patch14_siglip_gap_378.v2_webli` | 378 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_378.v2_webli) |
| `vit_so400m_patch16_siglip_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_256.v2_webli) |
| `vit_so400m_patch16_siglip_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_384.v2_webli) |
| `vit_so400m_patch16_siglip_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_512.v2_webli) |
| `vit_so400m_patch16_siglip_gap_256.v2_webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_gap_256.v2_webli) |
| `vit_so400m_patch16_siglip_gap_384.v2_webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_gap_384.v2_webli) |
| `vit_so400m_patch16_siglip_gap_512.v2_webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_gap_512.v2_webli) |

### `webli` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch14_reg1_tipsv2.webli` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch14_reg1_tipsv2.webli) |
| `vit_base_patch16_siglip_224.webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_224.webli) |
| `vit_base_patch16_siglip_256.webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_256.webli) |
| `vit_base_patch16_siglip_256.webli_i18n` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_256.webli_i18n) |
| `vit_base_patch16_siglip_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_384.webli) |
| `vit_base_patch16_siglip_512.webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_512.webli) |
| `vit_base_patch16_siglip_gap_224.webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_224.webli) |
| `vit_base_patch16_siglip_gap_256.webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_256.webli) |
| `vit_base_patch16_siglip_gap_256.webli_i18n` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_256.webli_i18n) |
| `vit_base_patch16_siglip_gap_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_384.webli) |
| `vit_base_patch16_siglip_gap_512.webli` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_siglip_gap_512.webli) |
| `vit_giant_patch14_reg1_tipsv2.webli` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giant_patch14_reg1_tipsv2.webli) |
| `vit_large_patch14_reg1_tipsv2.webli` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_reg1_tipsv2.webli) |
| `vit_large_patch16_siglip_256.webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_256.webli) |
| `vit_large_patch16_siglip_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_384.webli) |
| `vit_large_patch16_siglip_gap_256.webli` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_gap_256.webli) |
| `vit_large_patch16_siglip_gap_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_siglip_gap_384.webli) |
| `vit_so400m_patch14_reg1_tipsv2.webli` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_reg1_tipsv2.webli) |
| `vit_so400m_patch14_siglip_224.webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_224.webli) |
| `vit_so400m_patch14_siglip_378.webli` | 378 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_378.webli) |
| `vit_so400m_patch14_siglip_378.webli_ft_in1k` | 378 | 89.410 | 378 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_378.webli_ft_in1k) |
| `vit_so400m_patch14_siglip_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_384.webli) |
| `vit_so400m_patch14_siglip_gap_224.webli` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.webli) |
| `vit_so400m_patch14_siglip_gap_378.webli` | 378 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_378.webli) |
| `vit_so400m_patch14_siglip_gap_378.webli_ft_in1k` | 378 | 89.056 | 378 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_378.webli_ft_in1k) |
| `vit_so400m_patch14_siglip_gap_384.webli` | 384 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_384.webli) |
| `vit_so400m_patch16_siglip_256.webli_i18n` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_256.webli_i18n) |
| `vit_so400m_patch16_siglip_gap_256.webli_i18n` | 256 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch16_siglip_gap_256.webli_i18n) |

### `sbb` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_betwixt_patch16_reg1_gap_256.sbb_in1k` | 256 | 83.652 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg1_gap_256.sbb_in1k) |
| `vit_betwixt_patch16_reg4_gap_256.sbb_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb_in12k) |
| `vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k` | 256 | 85.426 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k) |
| `vit_betwixt_patch16_reg4_gap_256.sbb_in1k` | 256 | 83.710 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb_in1k) |
| `vit_dlittle_patch16_reg1_gap_256.sbb_nadamuon_in1k` | 256 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_dlittle_patch16_reg1_gap_256.sbb_nadamuon_in1k) |
| `vit_dpwee_patch16_reg1_gap_256.sbb_in1k` | 256 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_dpwee_patch16_reg1_gap_256.sbb_in1k) |
| `vit_dpwee_patch16_reg1_gap_256.sbb_nadamuon_in1k` | 256 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_dpwee_patch16_reg1_gap_256.sbb_nadamuon_in1k) |
| `vit_dwee_patch16_reg1_gap_256.sbb_in1k` | 256 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_dwee_patch16_reg1_gap_256.sbb_in1k) |
| `vit_dwee_patch16_reg1_gap_256.sbb_nadamuon_in1k` | 256 | - | - | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_dwee_patch16_reg1_gap_256.sbb_nadamuon_in1k) |
| `vit_little_patch16_reg1_gap_256.sbb_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_little_patch16_reg1_gap_256.sbb_in12k) |
| `vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k` | 256 | 83.800 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k) |
| `vit_little_patch16_reg4_gap_256.sbb_in1k` | 256 | 82.520 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) |
| `vit_medium_patch16_reg1_gap_256.sbb_in1k` | 256 | 83.462 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_reg1_gap_256.sbb_in1k) |
| `vit_medium_patch16_reg4_gap_256.sbb_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in12k) |
| `vit_medium_patch16_reg4_gap_256.sbb_in12k_ft_in1k` | 256 | 84.956 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in12k_ft_in1k) |
| `vit_medium_patch16_reg4_gap_256.sbb_in1k` | 256 | 83.466 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in1k) |
| `vit_mediumd_patch16_reg4_gap_256.sbb_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb_in12k) |
| `vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k` | 256 | 86.198 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k) |
| `vit_pwee_patch16_reg1_gap_256.sbb_in1k` | 256 | 80.082 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pwee_patch16_reg1_gap_256.sbb_in1k) |
| `vit_so150m2_patch16_reg1_gap_256.sbb_e200_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_256.sbb_e200_in12k) |
| `vit_so150m2_patch16_reg1_gap_256.sbb_e200_in12k_ft_in1k` | 256 | 87.318 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_256.sbb_e200_in12k_ft_in1k) |
| `vit_so150m2_patch16_reg1_gap_384.sbb_e200_in12k_ft_in1k` | 384 | 87.932 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_384.sbb_e200_in12k_ft_in1k) |
| `vit_so150m2_patch16_reg1_gap_448.sbb_e200_in12k_ft_in1k` | 448 | 88.074 | 448 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_448.sbb_e200_in12k_ft_in1k) |
| `vit_so150m_patch16_reg4_gap_256.sbb_e250_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m_patch16_reg4_gap_256.sbb_e250_in12k) |
| `vit_so150m_patch16_reg4_gap_256.sbb_e250_in12k_ft_in1k` | 256 | 86.720 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m_patch16_reg4_gap_256.sbb_e250_in12k_ft_in1k) |
| `vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k` | 384 | 87.370 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k) |
| `vit_wee_patch16_reg1_gap_256.sbb_in1k` | 256 | 80.262 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_wee_patch16_reg1_gap_256.sbb_in1k) |

### `augreg` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch8_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch8_224.augreg_in21k) |
| `vit_base_patch8_224.augreg_in21k_ft_in1k` | 224 | 85.838 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch8_224.augreg_in21k_ft_in1k) |
| `vit_base_patch16_224.augreg_in1k` | 224 | 79.154 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.augreg_in1k) |
| `vit_base_patch16_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.augreg_in21k) |
| `vit_base_patch16_224.augreg_in21k_ft_in1k` | 224 | 84.534 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.augreg_in21k_ft_in1k) |
| `vit_base_patch16_384.augreg_in1k` | 384 | 81.102 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_384.augreg_in1k) |
| `vit_base_patch16_384.augreg_in21k_ft_in1k` | 384 | 86.010 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_384.augreg_in21k_ft_in1k) |
| `vit_base_patch32_224.augreg_in1k` | 224 | 74.908 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_224.augreg_in1k) |
| `vit_base_patch32_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_224.augreg_in21k) |
| `vit_base_patch32_224.augreg_in21k_ft_in1k` | 224 | 80.732 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_224.augreg_in21k_ft_in1k) |
| `vit_base_patch32_384.augreg_in1k` | 384 | 78.750 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_384.augreg_in1k) |
| `vit_base_patch32_384.augreg_in21k_ft_in1k` | 384 | 83.358 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_384.augreg_in21k_ft_in1k) |
| `vit_large_patch16_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_224.augreg_in21k) |
| `vit_large_patch16_224.augreg_in21k_ft_in1k` | 224 | 85.856 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_224.augreg_in21k_ft_in1k) |
| `vit_large_patch16_384.augreg_in21k_ft_in1k` | 384 | 87.096 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_384.augreg_in21k_ft_in1k) |
| `vit_small_patch16_224.augreg_in1k` | 224 | 78.842 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_224.augreg_in1k) |
| `vit_small_patch16_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_224.augreg_in21k) |
| `vit_small_patch16_224.augreg_in21k_ft_in1k` | 224 | 81.402 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_224.augreg_in21k_ft_in1k) |
| `vit_small_patch16_384.augreg_in1k` | 384 | 81.130 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_384.augreg_in1k) |
| `vit_small_patch16_384.augreg_in21k_ft_in1k` | 384 | 83.814 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_384.augreg_in21k_ft_in1k) |
| `vit_small_patch32_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch32_224.augreg_in21k) |
| `vit_small_patch32_224.augreg_in21k_ft_in1k` | 224 | 76.010 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch32_224.augreg_in21k_ft_in1k) |
| `vit_small_patch32_384.augreg_in21k_ft_in1k` | 384 | 80.476 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch32_384.augreg_in21k_ft_in1k) |
| `vit_tiny_patch16_224.augreg_in21k` | 224 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k) |
| `vit_tiny_patch16_224.augreg_in21k_ft_in1k` | 224 | 75.452 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k_ft_in1k) |
| `vit_tiny_patch16_384.augreg_in21k_ft_in1k` | 384 | 78.438 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_tiny_patch16_384.augreg_in21k_ft_in1k) |

### `laion2b` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.laion2b` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b) |
| `vit_base_patch16_clip_224.laion2b_ft_in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in12k) |
| `vit_base_patch16_clip_224.laion2b_ft_in12k_in1k` | 224 | 86.204 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in12k_in1k) |
| `vit_base_patch16_clip_224.laion2b_ft_in1k` | 224 | 85.488 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in1k) |
| `vit_base_patch16_clip_384.laion2b_ft_in12k_in1k` | 384 | 87.210 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k) |
| `vit_base_patch16_clip_384.laion2b_ft_in1k` | 384 | 86.638 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in1k) |
| `vit_base_patch32_clip_224.laion2b` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b) |
| `vit_base_patch32_clip_224.laion2b_ft_in12k_in1k` | 224 | 83.304 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b_ft_in12k_in1k) |
| `vit_base_patch32_clip_224.laion2b_ft_in1k` | 224 | 82.614 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.laion2b_ft_in1k) |
| `vit_base_patch32_clip_384.laion2b_ft_in12k_in1k` | 384 | 85.398 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_384.laion2b_ft_in12k_in1k) |
| `vit_base_patch32_clip_448.laion2b_ft_in12k_in1k` | 448 | 85.792 | 448 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_448.laion2b_ft_in12k_in1k) |
| `vit_giant_patch14_clip_224.laion2b` | 224 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/vit_giant_patch14_clip_224.laion2b) |
| `vit_gigantic_patch14_clip_224.laion2b` | 224 | - | - | 1280 | apache-2.0 | [timm](https://huggingface.co/timm/vit_gigantic_patch14_clip_224.laion2b) |
| `vit_huge_patch14_clip_224.laion2b` | 224 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b) |
| `vit_huge_patch14_clip_224.laion2b_ft_in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b_ft_in12k) |
| `vit_huge_patch14_clip_224.laion2b_ft_in12k_in1k` | 224 | 88.288 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b_ft_in12k_in1k) |
| `vit_huge_patch14_clip_224.laion2b_ft_in1k` | 224 | 87.612 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.laion2b_ft_in1k) |
| `vit_huge_patch14_clip_336.laion2b_ft_in12k_in1k` | 336 | 88.634 | 336 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_336.laion2b_ft_in12k_in1k) |
| `vit_large_patch14_clip_224.laion2b` | 224 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.laion2b) |
| `vit_large_patch14_clip_224.laion2b_ft_in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.laion2b_ft_in12k) |
| `vit_large_patch14_clip_224.laion2b_ft_in12k_in1k` | 224 | 87.900 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.laion2b_ft_in12k_in1k) |
| `vit_large_patch14_clip_224.laion2b_ft_in1k` | 224 | 87.288 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.laion2b_ft_in1k) |
| `vit_large_patch14_clip_336.laion2b_ft_in12k_in1k` | 336 | 88.190 | 336 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_336.laion2b_ft_in12k_in1k) |
| `vit_large_patch14_clip_336.laion2b_ft_in1k` | 336 | 87.870 | 336 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_336.laion2b_ft_in1k) |

### `openai` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.openai` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.openai) |
| `vit_base_patch16_clip_224.openai_ft_in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in12k) |
| `vit_base_patch16_clip_224.openai_ft_in12k_in1k` | 224 | 85.954 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in12k_in1k) |
| `vit_base_patch16_clip_224.openai_ft_in1k` | 224 | 85.282 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.openai_ft_in1k) |
| `vit_base_patch16_clip_384.openai_ft_in12k_in1k` | 384 | 87.030 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_384.openai_ft_in12k_in1k) |
| `vit_base_patch16_clip_384.openai_ft_in1k` | 384 | 86.210 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_384.openai_ft_in1k) |
| `vit_base_patch16_clip_quickgelu_224.openai` | 224 | - | - | 512 | apache-2.0 | [timm/vit_base_patch16_clip_224.openai](https://huggingface.co/timm/vit_base_patch16_clip_224.openai) |
| `vit_base_patch32_clip_224.openai` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.openai) |
| `vit_base_patch32_clip_224.openai_ft_in1k` | 224 | 81.944 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.openai_ft_in1k) |
| `vit_base_patch32_clip_384.openai_ft_in12k_in1k` | 384 | 85.218 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_384.openai_ft_in12k_in1k) |
| `vit_base_patch32_clip_quickgelu_224.openai` | 224 | - | - | 512 | apache-2.0 | [timm/vit_base_patch32_clip_224.openai](https://huggingface.co/timm/vit_base_patch32_clip_224.openai) |
| `vit_large_patch14_clip_224.openai` | 224 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.openai) |
| `vit_large_patch14_clip_224.openai_ft_in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.openai_ft_in12k) |
| `vit_large_patch14_clip_224.openai_ft_in12k_in1k` | 224 | 88.162 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.openai_ft_in12k_in1k) |
| `vit_large_patch14_clip_224.openai_ft_in1k` | 224 | 87.858 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.openai_ft_in1k) |
| `vit_large_patch14_clip_336.openai` | 336 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_336.openai) |
| `vit_large_patch14_clip_336.openai_ft_in12k_in1k` | 336 | 88.260 | 336 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_336.openai_ft_in12k_in1k) |
| `vit_large_patch14_clip_quickgelu_224.openai` | 224 | - | - | 768 | apache-2.0 | [timm/vit_large_patch14_clip_224.openai](https://huggingface.co/timm/vit_large_patch14_clip_224.openai) |
| `vit_large_patch14_clip_quickgelu_336.openai` | 336 | - | - | 768 | apache-2.0 | [timm/vit_large_patch14_clip_336.openai](https://huggingface.co/timm/vit_large_patch14_clip_336.openai) |

### `metaclip` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.metaclip_2pt5b` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.metaclip_2pt5b) |
| `vit_base_patch16_clip_224.metaclip_400m` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.metaclip_400m) |
| `vit_base_patch16_clip_quickgelu_224.metaclip_2pt5b` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm/vit_base_patch16_clip_224.metaclip_2pt5b](https://huggingface.co/timm/vit_base_patch16_clip_224.metaclip_2pt5b) |
| `vit_base_patch16_clip_quickgelu_224.metaclip_400m` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm/vit_base_patch16_clip_224.metaclip_400m](https://huggingface.co/timm/vit_base_patch16_clip_224.metaclip_400m) |
| `vit_base_patch32_clip_224.metaclip_2pt5b` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.metaclip_2pt5b) |
| `vit_base_patch32_clip_224.metaclip_400m` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.metaclip_400m) |
| `vit_base_patch32_clip_quickgelu_224.metaclip_2pt5b` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm/vit_base_patch32_clip_224.metaclip_2pt5b](https://huggingface.co/timm/vit_base_patch32_clip_224.metaclip_2pt5b) |
| `vit_base_patch32_clip_quickgelu_224.metaclip_400m` | 224 | - | - | 512 | cc-by-nc-4.0 | [timm/vit_base_patch32_clip_224.metaclip_400m](https://huggingface.co/timm/vit_base_patch32_clip_224.metaclip_400m) |
| `vit_gigantic_patch14_clip_224.metaclip_2pt5b` | 224 | - | - | 1280 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_gigantic_patch14_clip_224.metaclip_2pt5b) |
| `vit_gigantic_patch14_clip_quickgelu_224.metaclip_2pt5b` | 224 | - | - | 1280 | cc-by-nc-4.0 | [timm/vit_gigantic_patch14_clip_224.metaclip_2pt5b](https://huggingface.co/timm/vit_gigantic_patch14_clip_224.metaclip_2pt5b) |
| `vit_huge_patch14_clip_224.metaclip_2pt5b` | 224 | - | - | 1024 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.metaclip_2pt5b) |
| `vit_huge_patch14_clip_224.metaclip_altogether` | 224 | - | - | 1024 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.metaclip_altogether) |
| `vit_huge_patch14_clip_quickgelu_224.metaclip_2pt5b` | 224 | - | - | 1024 | cc-by-nc-4.0 | [timm/vit_huge_patch14_clip_224.metaclip_2pt5b](https://huggingface.co/timm/vit_huge_patch14_clip_224.metaclip_2pt5b) |
| `vit_large_patch14_clip_224.metaclip_2pt5b` | 224 | - | - | 768 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.metaclip_2pt5b) |
| `vit_large_patch14_clip_224.metaclip_400m` | 224 | - | - | 768 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.metaclip_400m) |
| `vit_large_patch14_clip_quickgelu_224.metaclip_2pt5b` | 224 | - | - | 768 | cc-by-nc-4.0 | [timm/vit_large_patch14_clip_224.metaclip_2pt5b](https://huggingface.co/timm/vit_large_patch14_clip_224.metaclip_2pt5b) |
| `vit_large_patch14_clip_quickgelu_224.metaclip_400m` | 224 | - | - | 768 | cc-by-nc-4.0 | [timm/vit_large_patch14_clip_224.metaclip_400m](https://huggingface.co/timm/vit_large_patch14_clip_224.metaclip_400m) |

### `apple` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `aimv2_1b_patch14_224.apple_pt` | 224 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_1b_patch14_224.apple_pt) |
| `aimv2_1b_patch14_336.apple_pt` | 336 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_1b_patch14_336.apple_pt) |
| `aimv2_1b_patch14_448.apple_pt` | 448 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_1b_patch14_448.apple_pt) |
| `aimv2_3b_patch14_224.apple_pt` | 224 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_3b_patch14_224.apple_pt) |
| `aimv2_3b_patch14_336.apple_pt` | 336 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_3b_patch14_336.apple_pt) |
| `aimv2_3b_patch14_448.apple_pt` | 448 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_3b_patch14_448.apple_pt) |
| `aimv2_huge_patch14_224.apple_pt` | 224 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_huge_patch14_224.apple_pt) |
| `aimv2_huge_patch14_336.apple_pt` | 336 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_huge_patch14_336.apple_pt) |
| `aimv2_huge_patch14_448.apple_pt` | 448 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_huge_patch14_448.apple_pt) |
| `aimv2_large_patch14_224.apple_pt` | 224 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_large_patch14_224.apple_pt) |
| `aimv2_large_patch14_224.apple_pt_dist` | 224 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_large_patch14_224.apple_pt_dist) |
| `aimv2_large_patch14_336.apple_pt` | 336 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_large_patch14_336.apple_pt) |
| `aimv2_large_patch14_336.apple_pt_dist` | 336 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_large_patch14_336.apple_pt_dist) |
| `aimv2_large_patch14_448.apple_pt` | 448 | - | - | none | apple-ascl | [timm](https://huggingface.co/timm/aimv2_large_patch14_448.apple_pt) |
| `vit_large_patch14_clip_224.apple_mclip2_dfndr2b` | 224 | - | - | 768 | apple-amlr | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.apple_mclip2_dfndr2b) |

### `pali` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_so400m_patch14_siglip_gap_224.pali_mix` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.pali_mix) |
| `vit_so400m_patch14_siglip_gap_224.pali_pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.pali_pt) |
| `vit_so400m_patch14_siglip_gap_448.pali_mix` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali_mix) |
| `vit_so400m_patch14_siglip_gap_448.pali_ocrvqa` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali_ocrvqa) |
| `vit_so400m_patch14_siglip_gap_448.pali_pt` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali_pt) |
| `vit_so400m_patch14_siglip_gap_448.pali_refcoco_seg` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali_refcoco_seg) |
| `vit_so400m_patch14_siglip_gap_896.pali_ocrvqa` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_896.pali_ocrvqa) |
| `vit_so400m_patch14_siglip_gap_896.pali_pt` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_896.pali_pt) |
| `vit_so400m_patch14_siglip_gap_896.pali_refcoco_seg` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_896.pali_refcoco_seg) |

### `lvd142m` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch14_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch14_dinov2.lvd142m) |
| `vit_base_patch14_reg4_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch14_reg4_dinov2.lvd142m) |
| `vit_giant_patch14_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giant_patch14_dinov2.lvd142m) |
| `vit_giant_patch14_reg4_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_giant_patch14_reg4_dinov2.lvd142m) |
| `vit_large_patch14_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_dinov2.lvd142m) |
| `vit_large_patch14_reg4_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_reg4_dinov2.lvd142m) |
| `vit_small_patch14_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch14_dinov2.lvd142m) |
| `vit_small_patch14_reg4_dinov2.lvd142m` | 518 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch14_reg4_dinov2.lvd142m) |

### `orig` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_224.orig_in21k` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.orig_in21k) |
| `vit_base_patch16_224.orig_in21k_ft_in1k` | 224 | 81.782 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.orig_in21k_ft_in1k) |
| `vit_base_patch16_384.orig_in21k_ft_in1k` | 384 | 84.212 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_384.orig_in21k_ft_in1k) |
| `vit_base_patch32_224.orig_in21k` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_224.orig_in21k) |
| `vit_huge_patch14_224.orig_in21k` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_224.orig_in21k) |
| `vit_large_patch16_224.orig_in21k` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_224.orig_in21k) |
| `vit_large_patch32_224.orig_in21k` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch32_224.orig_in21k) |
| `vit_large_patch32_384.orig_in21k_ft_in1k` | 384 | 81.508 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch32_384.orig_in21k_ft_in1k) |

### `pali2` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_so400m_patch14_siglip_gap_224.pali2_10b_pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.pali2_10b_pt) |
| `vit_so400m_patch14_siglip_gap_224.pali2_3b_pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_224.pali2_3b_pt) |
| `vit_so400m_patch14_siglip_gap_448.pali2_10b_docci` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali2_10b_docci) |
| `vit_so400m_patch14_siglip_gap_448.pali2_10b_pt` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali2_10b_pt) |
| `vit_so400m_patch14_siglip_gap_448.pali2_3b_docci` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali2_3b_docci) |
| `vit_so400m_patch14_siglip_gap_448.pali2_3b_pt` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_448.pali2_3b_pt) |
| `vit_so400m_patch14_siglip_gap_896.pali2_10b_pt` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_896.pali2_10b_pt) |
| `vit_so400m_patch14_siglip_gap_896.pali2_3b_pt` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_so400m_patch14_siglip_gap_896.pali2_3b_pt) |

### `sbb2` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k) |
| `vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k` | 256 | 85.734 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k) |
| `vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k` | 384 | 86.618 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) |
| `vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k) |
| `vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k` | 256 | 86.608 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k) |
| `vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k` | 384 | 87.438 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) |

### `laion400m` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.laion400m_e32` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.laion400m_e32) |
| `vit_base_patch16_plus_clip_240.laion400m_e32` | 240 | - | - | 640 | mit | [timm](https://huggingface.co/timm/vit_base_patch16_plus_clip_240.laion400m_e32) |
| `vit_base_patch32_clip_224.laion400m_e32` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.laion400m_e32) |
| `vit_base_patch32_clip_quickgelu_224.laion400m_e32` | 224 | - | - | 512 | mit | [timm/vit_base_patch32_clip_224.laion400m_e32](https://huggingface.co/timm/vit_base_patch32_clip_224.laion400m_e32) |
| `vit_large_patch14_clip_224.laion400m_e32` | 224 | - | - | 768 | mit | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.laion400m_e32) |

### `metaclip2` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_gigantic_patch14_clip_224.metaclip2_worldwide` | 224 | - | - | 1280 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_gigantic_patch14_clip_224.metaclip2_worldwide) |
| `vit_gigantic_patch14_clip_378.metaclip2_worldwide` | 378 | - | - | 1280 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_gigantic_patch14_clip_378.metaclip2_worldwide) |
| `vit_huge_patch14_clip_224.metaclip2_worldwide` | 224 | - | - | 1024 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.metaclip2_worldwide) |
| `vit_huge_patch14_clip_378.metaclip2_worldwide` | 378 | - | - | 1024 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_378.metaclip2_worldwide) |
| `vit_huge_patch14_clip_quickgelu_224.metaclip2_worldwide` | 224 | - | - | 1024 | cc-by-nc-4.0 | [timm/vit_huge_patch14_clip_224.metaclip2_worldwide](https://huggingface.co/timm/vit_huge_patch14_clip_224.metaclip2_worldwide) |

### `datacompxl` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.datacompxl` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.datacompxl) |
| `vit_base_patch32_clip_224.datacompxl` | 224 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_224.datacompxl) |
| `vit_base_patch32_clip_256.datacompxl` | 256 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_clip_256.datacompxl) |
| `vit_large_patch14_clip_224.datacompxl` | 224 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.datacompxl) |

### `dfn2b` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_clip_224.dfn2b` | 224 | - | - | 512 | apple-ascl | [timm](https://huggingface.co/timm/vit_base_patch16_clip_224.dfn2b) |
| `vit_large_patch14_clip_224.dfn2b` | 224 | - | - | 768 | apple-ascl | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.dfn2b) |
| `vit_large_patch14_clip_224.dfn2b_s39b` | 224 | - | - | 768 | apple-ascl | [timm](https://huggingface.co/timm/vit_large_patch14_clip_224.dfn2b_s39b) |
| `vit_large_patch14_clip_quickgelu_224.dfn2b` | 224 | - | - | 768 | apple-ascl | [timm/vit_large_patch14_clip_224.dfn2b](https://huggingface.co/timm/vit_large_patch14_clip_224.dfn2b) |

### `dfn5b` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_huge_patch14_clip_224.dfn5b` | 224 | - | - | 1024 | apple-ascl | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_224.dfn5b) |
| `vit_huge_patch14_clip_378.dfn5b` | 378 | - | - | 1024 | apple-ascl | [timm](https://huggingface.co/timm/vit_huge_patch14_clip_378.dfn5b) |
| `vit_huge_patch14_clip_quickgelu_224.dfn5b` | 224 | - | - | 1024 | apple-ascl | [timm/vit_huge_patch14_clip_224.dfn5b](https://huggingface.co/timm/vit_huge_patch14_clip_224.dfn5b) |
| `vit_huge_patch14_clip_quickgelu_378.dfn5b` | 378 | - | - | 1024 | apple-ascl | [timm/vit_huge_patch14_clip_378.dfn5b](https://huggingface.co/timm/vit_huge_patch14_clip_378.dfn5b) |

### `dino` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch8_224.dino` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch8_224.dino) |
| `vit_base_patch16_224.dino` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.dino) |
| `vit_small_patch8_224.dino` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch8_224.dino) |
| `vit_small_patch16_224.dino` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_224.dino) |

### `indomain` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `beit3_base_patch16_224.indomain_in22k_ft_in1k` | 224 | 85.454 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/beit3_base_patch16_224.indomain_in22k_ft_in1k) |
| `beit3_base_patch16_224.indomain_pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/beit3_base_patch16_224.indomain_pt) |
| `beit3_large_patch16_224.indomain_in22k_ft_in1k` | 224 | 87.534 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/beit3_large_patch16_224.indomain_in22k_ft_in1k) |
| `beit3_large_patch16_224.indomain_pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/beit3_large_patch16_224.indomain_pt) |

### `sw` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_rpn_224.sw_in1k` | 224 | 82.218 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_rpn_224.sw_in1k) |
| `vit_medium_patch16_gap_240.sw_in12k` | 240 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_gap_240.sw_in12k) |
| `vit_medium_patch16_gap_256.sw_in12k_ft_in1k` | 256 | 84.442 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_gap_256.sw_in12k_ft_in1k) |
| `vit_medium_patch16_gap_384.sw_in12k_ft_in1k` | 384 | 85.556 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_medium_patch16_gap_384.sw_in12k_ft_in1k) |

### `tinyclip` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_betwixt_patch32_clip_224.tinyclip_laion400m` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_betwixt_patch32_clip_224.tinyclip_laion400m) |
| `vit_medium_patch16_clip_224.tinyclip_yfcc15m` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_medium_patch16_clip_224.tinyclip_yfcc15m) |
| `vit_medium_patch32_clip_224.tinyclip_laion400m` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_medium_patch32_clip_224.tinyclip_laion400m) |
| `vit_xsmall_patch16_clip_224.tinyclip_yfcc15m` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/vit_xsmall_patch16_clip_224.tinyclip_yfcc15m) |

### `mae` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_224.mae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.mae) |
| `vit_huge_patch14_224.mae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_huge_patch14_224.mae) |
| `vit_large_patch16_224.mae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/vit_large_patch16_224.mae) |

### `augreg2` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch8_224.augreg2_in21k_ft_in1k` | 224 | 86.252 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch8_224.augreg2_in21k_ft_in1k) |
| `vit_base_patch16_224.augreg2_in21k_ft_in1k` | 224 | 85.108 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.augreg2_in21k_ft_in1k) |

### `ogvl` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_intern300m_patch14_448.ogvl_2pt5` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_intern300m_patch14_448.ogvl_2pt5) |
| `vit_intern300m_patch14_448.ogvl_dist` | 448 | - | - | none | mit | [timm](https://huggingface.co/timm/vit_intern300m_patch14_448.ogvl_dist) |

### `sam` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_224.sam_in1k` | 224 | 80.246 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224.sam_in1k) |
| `vit_base_patch32_224.sam_in1k` | 224 | 73.704 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch32_224.sam_in1k) |

### Other

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `beit3_base_patch16_224.in22k_ft_in1k` | 224 | 85.390 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/beit3_base_patch16_224.in22k_ft_in1k) |
| `beit3_base_patch16_224.pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/beit3_base_patch16_224.pt) |
| `beit3_large_patch16_224.in22k_ft_in1k` | 224 | 87.628 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/beit3_large_patch16_224.in22k_ft_in1k) |
| `beit3_large_patch16_224.pt` | 224 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/beit3_large_patch16_224.pt) |
| `eva_large_patch14_196.in22k_ft_in1k` | 196 | 87.952 | 196 | 1000 | mit | [timm](https://huggingface.co/timm/eva_large_patch14_196.in22k_ft_in1k) |
| `eva_large_patch14_196.in22k_ft_in22k_in1k` | 196 | 88.590 | 196 | 1000 | mit | [timm](https://huggingface.co/timm/eva_large_patch14_196.in22k_ft_in22k_in1k) |
| `eva_large_patch14_336.in22k_ft_in1k` | 336 | 88.680 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva_large_patch14_336.in22k_ft_in1k) |
| `eva_large_patch14_336.in22k_ft_in22k_in1k` | 336 | 89.238 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva_large_patch14_336.in22k_ft_in22k_in1k) |
| `flexivit_base.1000ep_in21k` | 240 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.1000ep_in21k) |
| `flexivit_base.1200ep_in1k` | 240 | 84.678 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.1200ep_in1k) |
| `flexivit_base.300ep_in1k` | 240 | 84.402 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.300ep_in1k) |
| `flexivit_base.300ep_in21k` | 240 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.300ep_in21k) |
| `flexivit_base.600ep_in1k` | 240 | 84.564 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.600ep_in1k) |
| `flexivit_base.patch16_in21k` | 240 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.patch16_in21k) |
| `flexivit_base.patch30_in21k` | 240 | - | - | 21843 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_base.patch30_in21k) |
| `flexivit_large.1200ep_in1k` | 240 | 85.646 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_large.1200ep_in1k) |
| `flexivit_large.300ep_in1k` | 240 | 85.284 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_large.300ep_in1k) |
| `flexivit_large.600ep_in1k` | 240 | 85.530 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_large.600ep_in1k) |
| `flexivit_small.1200ep_in1k` | 240 | 82.576 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_small.1200ep_in1k) |
| `flexivit_small.300ep_in1k` | 240 | 82.170 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_small.300ep_in1k) |
| `flexivit_small.600ep_in1k` | 240 | 82.388 | 240 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/flexivit_small.600ep_in1k) |
| `test_vit.r160_in1k` | 160 | 40.982 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_vit.r160_in1k) |
| `test_vit2.r160_in1k` | 160 | 42.250 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_vit2.r160_in1k) |
| `test_vit3.r160_in1k` | 160 | 56.908 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_vit3.r160_in1k) |
| `vit_base_patch16_224_miil.in21k` | 224 | - | - | 11221 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224_miil.in21k) |
| `vit_base_patch16_224_miil.in21k_ft_in1k` | 224 | 84.278 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_224_miil.in21k_ft_in1k) |
| `vit_giant_patch16_gap_224.in22k_ijepa` | 224 | - | - | none | cc-by-nc-4.0 | [original](https://dl.fbaipublicfiles.com/ijepa/IN22K-vit.g.16-600e.pth.tar) |
| `vit_huge_patch14_gap_224.in1k_ijepa` | 224 | - | - | none | cc-by-nc-4.0 | [original](https://dl.fbaipublicfiles.com/ijepa/IN1K-vit.h.14-300e.pth.tar) |
| `vit_huge_patch14_gap_224.in22k_ijepa` | 224 | - | - | none | cc-by-nc-4.0 | [original](https://dl.fbaipublicfiles.com/ijepa/IN22K-vit.h.14-900e.pth.tar) |
| `vit_huge_patch16_gap_448.in1k_ijepa` | 448 | - | - | none | cc-by-nc-4.0 | [original](https://dl.fbaipublicfiles.com/ijepa/IN1K-vit.h.16-448px-300e.pth.tar) |