# EVA

**Category:** ViT · **Code:**
[`timm/models/eva.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/eva.py) ·
**Architectures:** 65 · **Pretrained weights:** 83 (28 with ImageNet-1k results)

EVA and EVA-02 Vision Transformers and other ViT variants sharing the `Eva` class, with rotary position embeddings
(RoPE), SwiGLU MLPs and related additions. The module also holds the Perception Encoder (PE), ROPE-ViT, DINOv3,
LingBot-Vision and Sapiens2 models and `timm` original ViT configs with RoPE.

## Papers

* [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://arxiv.org/abs/2211.07636)
* [EVA-02: A Visual Representation for Neon Genesis](https://arxiv.org/abs/2303.11331)
* [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://arxiv.org/abs/2303.15389)
* [Perception Encoder: The best visual embeddings are not at the output of the
  network](https://arxiv.org/abs/2504.13181)
* [Rotary Position Embedding for Vision Transformer](https://arxiv.org/abs/2403.13298)
* [DINOv3](https://arxiv.org/abs/2508.10104)
* [Vision Pretraining for Dense Spatial Perception](https://arxiv.org/abs/2607.05247)
* [Sapiens2](https://arxiv.org/abs/2604.21681)

## 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('eva02_small_patch14_336.mim_in22k_ft_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `Eva` |
|---|---|
| [`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 (`Eva` with `vit_tiny_patch16_dinov3_qkvb` at
256), 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 |
|---|---:|---:|---:|---:|
| `eva02_base_patch14_224` | 85.76 | 23.22 | 224 | 1 |
| `eva02_base_patch14_448` | 87.12 | 107.11 | 448 | 3 |
| `eva02_base_patch16_clip_224` | 86.26 | 17.62 | 224 | 1 |
| `eva02_enormous_patch14_clip_224` | 4350.56 | 1132.46 | 224 | 2 |
| `eva02_large_patch14_224` | 303.27 | 81.15 | 224 | 2 |
| `eva02_large_patch14_448` | 305.08 | 362.33 | 448 | 6 |
| `eva02_large_patch14_clip_224` | 304.11 | 81.18 | 224 | 1 |
| `eva02_large_patch14_clip_336` | 304.43 | 191.34 | 336 | 1 |
| `eva02_small_patch14_224` | 21.62 | 6.14 | 224 | 1 |
| `eva02_small_patch14_336` | 22.13 | 15.48 | 336 | 1 |
| `eva02_tiny_patch14_224` | 5.50 | 1.70 | 224 | 1 |
| `eva02_tiny_patch14_336` | 5.76 | 4.68 | 336 | 1 |
| `eva_giant_patch14_224` | 1012.56 | 267.18 | 224 | 1 |
| `eva_giant_patch14_336` | 1013.01 | 620.64 | 336 | 2 |
| `eva_giant_patch14_560` | 1014.45 | 1906.76 | 560 | 1 |
| `eva_giant_patch14_clip_224` | 1012.59 | 267.18 | 224 | 2 |
| `vit_5b_patch16_sapiens2` | 5066.90 | - | 1024x768 | 1 |
| `vit_7b_patch16_dinov3` | 6716.03 | 1775.10 | 256 | 2 |
| `vit_base_patch16_dinov3` | 85.64 | 23.60 | 256 | 1 |
| `vit_base_patch16_dinov3_qkvb` | 85.66 | 23.60 | 256 | 2 |
| `vit_base_patch16_lingbot` | 85.66 | - | 512 | 1 |
| `vit_base_patch16_rope_224` | 86.43 | 17.58 | 224 | 1 |
| `vit_base_patch16_rope_ape_224` | 86.59 | 17.58 | 224 | 1 |
| `vit_base_patch16_rope_mixed_224` | 86.44 | 17.58 | 224 | 1 |
| `vit_base_patch16_rope_mixed_ape_224` | 86.59 | 17.58 | 224 | 1 |
| `vit_base_patch16_rope_reg1_gap_256` | 86.43 | 23.22 | 256 | 1 |
| `vit_base_patch16_sapiens2` | 113.99 | - | 1024x768 | 1 |
| `vit_betwixt_patch16_rope_reg4_gap_256` | 60.23 | 16.52 | 256 | 1 |
| `vit_giant_patch16_lingbot` | 1134.47 | - | 512 | 1 |
| `vit_giant_patch16_sapiens2` | 1455.47 | - | 1024x768 | 1 |
| `vit_huge_patch16_sapiens2` | 814.28 | - | 1024x768 | 1 |
| `vit_huge_plus_patch16_dinov3` | 840.51 | 224.88 | 256 | 1 |
| `vit_huge_plus_patch16_dinov3_qkvb` | 840.59 | 224.88 | 256 | 1 |
| `vit_large_patch16_dinov3` | 303.08 | 82.43 | 256 | 2 |
| `vit_large_patch16_dinov3_qkvb` | 303.13 | 82.43 | 256 | 2 |
| `vit_large_patch16_lingbot` | 303.13 | - | 512 | 1 |
| `vit_large_patch16_rope_224` | 304.17 | 61.60 | 224 | 1 |
| `vit_large_patch16_rope_ape_224` | 304.37 | 61.60 | 224 | 1 |
| `vit_large_patch16_rope_mixed_224` | 304.20 | 61.60 | 224 | 1 |
| `vit_large_patch16_rope_mixed_ape_224` | 304.40 | 61.60 | 224 | 1 |
| `vit_large_patch16_sapiens2` | 395.45 | - | 1024x768 | 1 |
| `vit_medium_patch16_rope_reg1_gap_256` | 38.74 | 10.63 | 256 | 1 |
| `vit_mediumd_patch16_rope_reg1_gap_256` | 63.95 | 17.65 | 256 | 1 |
| `vit_pe_core_base_patch16_224` | 93.67 | 17.82 | 224 | 1 |
| `vit_pe_core_gigantic_patch14_448` | 1882.03 | 2060.12 | 448 | 1 |
| `vit_pe_core_large_patch14_336` | 317.15 | 192.33 | 336 | 1 |
| `vit_pe_core_small_patch16_384` | 23.78 | 15.69 | 384 | 1 |
| `vit_pe_core_tiny_patch16_384` | 6.14 | 4.74 | 384 | 1 |
| `vit_pe_lang_gigantic_patch14_448` | 1740.92 | 1931.99 | 448 | 2 |
| `vit_pe_lang_large_patch14_448` | 291.42 | 346.99 | 448 | 2 |
| `vit_pe_spatial_base_patch16_512` | 86.43 | 107.13 | 512 | 1 |
| `vit_pe_spatial_gigantic_patch14_448` | 1851.89 | 2055.25 | 448 | 1 |
| `vit_pe_spatial_large_patch14_448` | 303.96 | 362.05 | 448 | 1 |
| `vit_pe_spatial_small_patch16_512` | 21.98 | 31.80 | 512 | 1 |
| `vit_pe_spatial_tiny_patch16_512` | 5.68 | 10.46 | 512 | 1 |
| `vit_small_patch16_dinov3` | 21.59 | 6.26 | 256 | 1 |
| `vit_small_patch16_dinov3_qkvb` | 21.60 | 6.26 | 256 | 2 |
| `vit_small_patch16_lingbot` | 21.60 | - | 512 | 1 |
| `vit_small_patch16_rope_224` | 21.98 | 4.61 | 224 | 1 |
| `vit_small_patch16_rope_ape_224` | 22.06 | 4.61 | 224 | 1 |
| `vit_small_patch16_rope_mixed_224` | 21.99 | 4.61 | 224 | 1 |
| `vit_small_patch16_rope_mixed_ape_224` | 22.06 | 4.61 | 224 | 1 |
| `vit_small_plus_patch16_dinov3` | 28.68 | 8.11 | 256 | 1 |
| `vit_small_plus_patch16_dinov3_qkvb` | 28.69 | 8.11 | 256 | 1 |
| `vit_tiny_patch16_dinov3_qkvb` | 5.49 | - | 256 | 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.

### `mim` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva02_base_patch14_224.mim_in22k` | 224 | - | - | none | mit | [timm](https://huggingface.co/timm/eva02_base_patch14_224.mim_in22k) |
| `eva02_base_patch14_448.mim_in22k_ft_in1k` | 448 | 88.262 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_base_patch14_448.mim_in22k_ft_in1k) |
| `eva02_base_patch14_448.mim_in22k_ft_in22k` | 448 | - | - | 21841 | mit | [timm](https://huggingface.co/timm/eva02_base_patch14_448.mim_in22k_ft_in22k) |
| `eva02_base_patch14_448.mim_in22k_ft_in22k_in1k` | 448 | 88.678 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1k) |
| `eva02_large_patch14_224.mim_in22k` | 224 | - | - | none | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_224.mim_in22k) |
| `eva02_large_patch14_224.mim_m38m` | 224 | - | - | none | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_224.mim_m38m) |
| `eva02_large_patch14_448.mim_in22k_ft_in1k` | 448 | 89.634 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_in22k_ft_in1k) |
| `eva02_large_patch14_448.mim_in22k_ft_in22k` | 448 | - | - | 21841 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_in22k_ft_in22k) |
| `eva02_large_patch14_448.mim_in22k_ft_in22k_in1k` | 448 | 89.956 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_in22k_ft_in22k_in1k) |
| `eva02_large_patch14_448.mim_m38m_ft_in1k` | 448 | 89.550 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_m38m_ft_in1k) |
| `eva02_large_patch14_448.mim_m38m_ft_in22k` | 448 | - | - | 21841 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_m38m_ft_in22k) |
| `eva02_large_patch14_448.mim_m38m_ft_in22k_in1k` | 448 | 90.056 | 448 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_448.mim_m38m_ft_in22k_in1k) |
| `eva02_small_patch14_224.mim_in22k` | 224 | - | - | none | mit | [timm](https://huggingface.co/timm/eva02_small_patch14_224.mim_in22k) |
| `eva02_small_patch14_336.mim_in22k_ft_in1k` | 336 | 85.770 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_small_patch14_336.mim_in22k_ft_in1k) |
| `eva02_tiny_patch14_224.mim_in22k` | 224 | - | - | none | mit | [timm](https://huggingface.co/timm/eva02_tiny_patch14_224.mim_in22k) |
| `eva02_tiny_patch14_336.mim_in22k_ft_in1k` | 336 | 80.648 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva02_tiny_patch14_336.mim_in22k_ft_in1k) |

### `fb` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_pe_core_base_patch16_224.fb` | 224 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_core_base_patch16_224.fb) |
| `vit_pe_core_gigantic_patch14_448.fb` | 448 | - | - | 1280 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_core_gigantic_patch14_448.fb) |
| `vit_pe_core_large_patch14_336.fb` | 336 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_core_large_patch14_336.fb) |
| `vit_pe_core_small_patch16_384.fb` | 384 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_core_small_patch16_384.fb) |
| `vit_pe_core_tiny_patch16_384.fb` | 384 | - | - | 512 | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_core_tiny_patch16_384.fb) |
| `vit_pe_lang_gigantic_patch14_448.fb` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_lang_gigantic_patch14_448.fb) |
| `vit_pe_lang_gigantic_patch14_448.fb_tiling` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_lang_gigantic_patch14_448.fb_tiling) |
| `vit_pe_lang_large_patch14_448.fb` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_lang_large_patch14_448.fb) |
| `vit_pe_lang_large_patch14_448.fb_tiling` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_lang_large_patch14_448.fb_tiling) |
| `vit_pe_spatial_base_patch16_512.fb` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_spatial_base_patch16_512.fb) |
| `vit_pe_spatial_gigantic_patch14_448.fb` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_spatial_gigantic_patch14_448.fb) |
| `vit_pe_spatial_large_patch14_448.fb` | 448 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_spatial_large_patch14_448.fb) |
| `vit_pe_spatial_small_patch16_512.fb` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_spatial_small_patch16_512.fb) |
| `vit_pe_spatial_tiny_patch16_512.fb` | 512 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/vit_pe_spatial_tiny_patch16_512.fb) |

### `naver` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_rope_224.naver_in1k` | 224 | 83.714 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_rope_224.naver_in1k) |
| `vit_base_patch16_rope_ape_224.naver_in1k` | 224 | 83.780 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_rope_ape_224.naver_in1k) |
| `vit_base_patch16_rope_mixed_224.naver_in1k` | 224 | 83.806 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_rope_mixed_224.naver_in1k) |
| `vit_base_patch16_rope_mixed_ape_224.naver_in1k` | 224 | 83.898 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_base_patch16_rope_mixed_ape_224.naver_in1k) |
| `vit_large_patch16_rope_224.naver_in1k` | 224 | 84.646 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_rope_224.naver_in1k) |
| `vit_large_patch16_rope_ape_224.naver_in1k` | 224 | 84.660 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_rope_ape_224.naver_in1k) |
| `vit_large_patch16_rope_mixed_224.naver_in1k` | 224 | 84.840 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_rope_mixed_224.naver_in1k) |
| `vit_large_patch16_rope_mixed_ape_224.naver_in1k` | 224 | 84.846 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_large_patch16_rope_mixed_ape_224.naver_in1k) |
| `vit_small_patch16_rope_224.naver_in1k` | 224 | 81.222 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_rope_224.naver_in1k) |
| `vit_small_patch16_rope_ape_224.naver_in1k` | 224 | 81.016 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_rope_ape_224.naver_in1k) |
| `vit_small_patch16_rope_mixed_224.naver_in1k` | 224 | 81.252 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_rope_mixed_224.naver_in1k) |
| `vit_small_patch16_rope_mixed_ape_224.naver_in1k` | 224 | 80.974 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/vit_small_patch16_rope_mixed_ape_224.naver_in1k) |

### `lvd1689m` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_7b_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_7b_patch16_dinov3.lvd1689m) |
| `vit_base_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_base_patch16_dinov3.lvd1689m) |
| `vit_base_patch16_dinov3_qkvb.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_base_patch16_dinov3_qkvb.lvd1689m) |
| `vit_huge_plus_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_huge_plus_patch16_dinov3.lvd1689m) |
| `vit_huge_plus_patch16_dinov3_qkvb.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_huge_plus_patch16_dinov3_qkvb.lvd1689m) |
| `vit_large_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_large_patch16_dinov3.lvd1689m) |
| `vit_large_patch16_dinov3_qkvb.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_large_patch16_dinov3_qkvb.lvd1689m) |
| `vit_small_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_small_patch16_dinov3.lvd1689m) |
| `vit_small_patch16_dinov3_qkvb.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_small_patch16_dinov3_qkvb.lvd1689m) |
| `vit_small_plus_patch16_dinov3.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_small_plus_patch16_dinov3.lvd1689m) |
| `vit_small_plus_patch16_dinov3_qkvb.lvd1689m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_small_plus_patch16_dinov3_qkvb.lvd1689m) |

### Sapiens2

Pretrained configs reference [Sapiens2](https://arxiv.org/abs/2604.21681).

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_5b_patch16_sapiens2.fb` | 1024x768 | - | - | none | sapiens2-license | [timm](https://huggingface.co/timm/vit_5b_patch16_sapiens2.fb) |
| `vit_base_patch16_sapiens2.fb` | 1024x768 | - | - | none | sapiens2-license | [timm](https://huggingface.co/timm/vit_base_patch16_sapiens2.fb) |
| `vit_giant_patch16_sapiens2.fb` | 1024x768 | - | - | none | sapiens2-license | [timm](https://huggingface.co/timm/vit_giant_patch16_sapiens2.fb) |
| `vit_huge_patch16_sapiens2.fb` | 1024x768 | - | - | none | sapiens2-license | [timm](https://huggingface.co/timm/vit_huge_patch16_sapiens2.fb) |
| `vit_large_patch16_sapiens2.fb` | 1024x768 | - | - | none | sapiens2-license | [timm](https://huggingface.co/timm/vit_large_patch16_sapiens2.fb) |

### `merged2b` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva02_base_patch16_clip_224.merged2b` | 224 | - | - | 512 | mit | [timm](https://huggingface.co/timm/eva02_base_patch16_clip_224.merged2b) |
| `eva02_large_patch14_clip_224.merged2b` | 224 | - | - | 768 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_clip_224.merged2b) |
| `eva02_large_patch14_clip_336.merged2b` | 336 | - | - | 768 | mit | [timm](https://huggingface.co/timm/eva02_large_patch14_clip_336.merged2b) |
| `eva_giant_patch14_clip_224.merged2b` | 224 | - | - | 1024 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_clip_224.merged2b) |

### `sbb` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_rope_reg1_gap_256.sbb_in1k` | 256 | 83.872 | 256 | 1000 | mit | [timm](https://huggingface.co/timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k) |
| `vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k` | 256 | 83.906 | 256 | 1000 | mit | [timm](https://huggingface.co/timm/vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k) |
| `vit_medium_patch16_rope_reg1_gap_256.sbb_in1k` | 256 | 83.810 | 256 | 1000 | mit | [timm](https://huggingface.co/timm/vit_medium_patch16_rope_reg1_gap_256.sbb_in1k) |
| `vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k` | 256 | 84.316 | 256 | 1000 | mit | [timm](https://huggingface.co/timm/vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k) |

### Vision Pretraining for Dense Spatial Perception

Pretrained configs reference [Vision Pretraining for Dense Spatial Perception](https://arxiv.org/abs/2607.05247).

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_lingbot.robbyant` | 512 | - | - | none | apache-2.0 | [belfner/vit_base_patch16_lingbot.robbyant](https://huggingface.co/belfner/vit_base_patch16_lingbot.robbyant) |
| `vit_giant_patch16_lingbot.robbyant` | 512 | - | - | none | apache-2.0 | [belfner/vit_giant_patch16_lingbot.robbyant](https://huggingface.co/belfner/vit_giant_patch16_lingbot.robbyant) |
| `vit_large_patch16_lingbot.robbyant` | 512 | - | - | none | apache-2.0 | [belfner/vit_large_patch16_lingbot.robbyant](https://huggingface.co/belfner/vit_large_patch16_lingbot.robbyant) |
| `vit_small_patch16_lingbot.robbyant` | 512 | - | - | none | apache-2.0 | [belfner/vit_small_patch16_lingbot.robbyant](https://huggingface.co/belfner/vit_small_patch16_lingbot.robbyant) |

### `eupe` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_base_patch16_dinov3_qkvb.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/vit_base_patch16_dinov3_qkvb.eupe_lvd1689m) |
| `vit_small_patch16_dinov3_qkvb.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/vit_small_patch16_dinov3_qkvb.eupe_lvd1689m) |
| `vit_tiny_patch16_dinov3_qkvb.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/vit_tiny_patch16_dinov3_qkvb.eupe_lvd1689m) |

### `sat493m` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `vit_7b_patch16_dinov3.sat493m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_7b_patch16_dinov3.sat493m) |
| `vit_large_patch16_dinov3.sat493m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_large_patch16_dinov3.sat493m) |
| `vit_large_patch16_dinov3_qkvb.sat493m` | 256 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/vit_large_patch16_dinov3_qkvb.sat493m) |

### `clip` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva_giant_patch14_224.clip_ft_in1k` | 224 | 88.896 | 224 | 1000 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_224.clip_ft_in1k) |
| `eva_giant_patch14_336.clip_ft_in1k` | 336 | 89.462 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_336.clip_ft_in1k) |

### `laion2b` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva02_enormous_patch14_clip_224.laion2b` | 224 | - | - | 1024 | mit | [timm](https://huggingface.co/timm/eva02_enormous_patch14_clip_224.laion2b) |
| `eva02_enormous_patch14_clip_224.laion2b_plus` | 224 | - | - | 1024 | mit | [timm](https://huggingface.co/timm/eva02_enormous_patch14_clip_224.laion2b_plus) |

### `m30m` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva_giant_patch14_336.m30m_ft_in22k_in1k` | 336 | 89.566 | 336 | 1000 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_336.m30m_ft_in22k_in1k) |
| `eva_giant_patch14_560.m30m_ft_in22k_in1k` | 560 | 89.790 | 560 | 1000 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_560.m30m_ft_in22k_in1k) |

### Other

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `eva_giant_patch14_clip_224.laion400m` | 224 | - | - | 1024 | mit | [timm](https://huggingface.co/timm/eva_giant_patch14_clip_224.laion400m) |

## Citation

```bibtex
@article{EVA,
  title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
  author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang,
  Tiejun and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2211.07636},
  year={2022}
}

@article{EVA02,
  title={EVA-02: A Visual Representation for Neon Genesis},
  author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2303.11331},
  year={2023}
}

@article{bolya2025perception,
  title={Perception encoder: The best visual embeddings are not at the output of the network},
  author={Bolya, Daniel and Huang, Po-Yao and Sun, Peize and Cho, Jang Hyun and Madotto, Andrea and Wei, Chen and Ma,
    Tengyu and Zhi, Jiale and Rajasegaran, Jathushan and Rasheed, Hanoona and others},
  journal={arXiv preprint arXiv:2504.13181},
  year={2025}
}

@inproceedings{heo2024rotary,
  title={Rotary position embedding for vision transformer},
  author={Heo, Byeongho and Park, Song and Han, Dongyoon and Yun, Sangdoo},
  booktitle={European Conference on Computer Vision},
  pages={289--305},
  year={2024},
  organization={Springer}
}

@article{simeoni2025dinov3,
  title={{DINOv3}},
  author={Sim{'e}oni, Oriane and Vo, Huy V. and Seitzer, Maximilian and Baldassarre, Federico and Oquab, Maxime
    and Jose, Cijo and Khalidov, Vasil and Szafraniec, Marc and Yi, Seungeun and Ramamonjisoa, Micha{"e}l
    and Massa, Francisco and Haziza, Daniel and Wehrstedt, Luca and Wang, Jianyuan and Darcet, Timoth{'e}e
    and Moutakanni, Th{'e}o and Sentana, Leonel and Roberts, Claire and Vedaldi, Andrea and Tolan, Jamie
    and Brandt, John and Couprie, Camille and Mairal, Julien and J{'e}gou, Herv{'e} and Labatut, Patrick
    and Bojanowski, Piotr},
  year={2025},
  eprint={2508.10104},
  url={https://arxiv.org/abs/2508.10104},
}

@article{lingbot-vision2026,
  title={Vision Pretraining for Dense Spatial Perception},
  author={Fu, Zelin and Tan, Bin and Sun, Changjiang and Liu, Shaohui and Zheng, Kecheng and Xu, Yinghao
    and Zhu, Xing and Shen, Yujun and Xue, Nan},
  journal={arXiv preprint arXiv:2607.05247},
  year={2026}
}

@article{khirodkarsapiens2,
  title={Sapiens2},
  author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Su, Zhaoen and Saito, Shunsuke},
  journal={arXiv preprint arXiv:2604.21681},
  year={2026}
}
```