# Image Feature Extraction Models: Open-Weight AI Source: https://savrn.com/models/tasks/image-feature-extraction Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Image Feature Extraction Models 18 open-weight image feature extraction models in the SAVRN Model Hub, with RKNNAI, AI at Meta and PyTorch Image Models publishing the most. 18Models 12Publishers 9M to 1BParameter range 3Licenses ## SAVRN's Take Every model here does one job: it takes an image in and hands back a set of numbers that describe it, so downstream systems can search or compare by those numbers. Six are indexed, all Vision Transformers, and they are tiny next to anything else we price. The 22M-parameter dinov2-small needs 0.1 GB at 16-bit; dinov2-large, at 304M parameters, needs 0.7 GB, and that is the whole range. None fills a card, so the question is how many image streams one GPU carries, not how many GPUs you need. The cheapest hosted entry for all six is a single MI300X at $1.85 an hour. AI at Meta wrote three of the six and holds the top two download slots: dinov2-base at 87M parameters draws 3,364,437 downloads a month and dinov2-small draws 3,240,723. Google's vit-base-patch16-224-in21k, pre-trained on ImageNet-21k's 14 million images across 21,843 classes at 224 by 224, sits third at 1,800,290. Five of the six carry Apache 2.0, so commercial use, modification and redistribution need no further permission. The exception is Camenduru's 303M-parameter dinov3-vitl16-pretrain-lvd1689m, filed under a license the index records only as other, and a buyer reads those terms line by line before production. Two more checks. Match the serving stack: five load through transformers, the timm build through timm. And skip quantization; dinov2-large drops from 0.7 GB to 0.4 GB at 8-bit and 0.2 GB at 4-bit, the small ones round to zero. Run at 16-bit, put the effort into batch size, and price the job in images per hour on that $1.85 card. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [dinov2-base](https://savrn.com/models/dinov2-base) | AI at Meta | 87M | apache-2.0 | 3.1M | 1x MI300X, $1.85/hr | | [dinov2-small](https://savrn.com/models/dinov2-small) | AI at Meta | 22M | apache-2.0 | 2.7M | 1x MI300X, $1.85/hr | | [vit_small_patch14_dinov2.lvd142m](https://savrn.com/models/vit-small-patch14-dinov2-lvd142m) | PyTorch Image Models | 22M | apache-2.0 | 2.1M | 1x MI300X, $1.85/hr | | [vit-base-patch16-224-in21k](https://savrn.com/models/vit-base-patch16-224-in21k) | Google | 86M | apache-2.0 | 1.1M | 1x MI300X, $1.85/hr | | [dinov2-large](https://savrn.com/models/dinov2-large) | AI at Meta | 304M | apache-2.0 | 1M | 1x MI300X, $1.85/hr | | [dinov3-vitl16-pretrain-lvd1689m](https://savrn.com/models/dinov3-vitl16-pretrain-lvd1689m) | Camenduru | 303M | other | 738.6k | 1x MI300X, $1.85/hr | | [clip-vitb-mini-distilled](https://savrn.com/models/clip-vitb-mini-distilled) | AbstractPhila | 9M | apache-2.0 | 64 | 1x MI300X, $1.85/hr | | [I-JEPA-Agro](https://savrn.com/models/i-jepa-agro) | Junior R F Junior | — | mit | — | — | | [IM-Animation-Motion-Encoder](https://savrn.com/models/im-animation-motion-encoder) | Fynn | — | apache-2.0 | — | — | | [RK182X-VIT-siglip2-so400m-patch14-384](https://savrn.com/models/rk182x-vit-siglip2-so400m-patch14-384) | RKNNAI | — | apache-2.0 | — | — | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 11 | Yes | | other | 6 | Read the license | | [mit](https://savrn.com/models/licenses/mit) | 1 | Yes | ## Who Publishes Them | Publisher | Models | | --- | --- | | [RKNNAI](https://savrn.com/model-publishers/rknnai) | 5 | | [AI at Meta](https://savrn.com/model-publishers/facebook) | 3 | | [PyTorch Image Models](https://savrn.com/model-publishers/timm) | 1 | | [Fynn](https://savrn.com/model-publishers/rbaerk) | 1 | | [Park](https://savrn.com/model-publishers/raspie) | 1 | | [Junior R F Junior](https://savrn.com/model-publishers/joserfjunior) | 1 | ## All 18 Models Model · Image feature extraction ### [dinov2-base](https://savrn.com/models/dinov2-base) [AI at Meta](https://savrn.com/model-publishers/facebook) Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features without Supervision by Oquab et al. and first released in this repository. Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One… Open weights apache-2.0 87M parameters transformers [View model](https://savrn.com/models/dinov2-base) Model · Image feature extraction ### [dinov2-small](https://savrn.com/models/dinov2-small) [AI at Meta](https://savrn.com/model-publishers/facebook) Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features without Supervision by Oquab et al. and first released in this repository. Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One… Open weights apache-2.0 22M parameters transformers [View model](https://savrn.com/models/dinov2-small) Model · Image feature extraction ### [vit_small_patch14_dinov2.lvd142m](https://savrn.com/models/vit-small-patch14-dinov2-lvd142m) [PyTorch Image Models](https://savrn.com/model-publishers/timm) A Vision Transformer (ViT) image feature model. Pretrained on LVD-142M with self-supervised DINOv2 method. - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 Explore the dataset and runtime metrics of this model in timm model results. Open weights apache-2.0 22M parameters timm [View model](https://savrn.com/models/vit-small-patch14-dinov2-lvd142m) Model · Image feature extraction ### [vit-base-patch16-224-in21k](https://savrn.com/models/vit-base-patch16-224-in21k) [Google](https://savrn.com/model-publishers/google) Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a… Open weights apache-2.0 86M parameters transformers [View model](https://savrn.com/models/vit-base-patch16-224-in21k) Model · Image feature extraction ### [dinov2-large](https://savrn.com/models/dinov2-large) [AI at Meta](https://savrn.com/model-publishers/facebook) Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features without Supervision by Oquab et al. and first released in this repository. Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One… Open weights apache-2.0 304M parameters transformers [View model](https://savrn.com/models/dinov2-large) Model · Image feature extraction ### [dinov3-vitl16-pretrain-lvd1689m](https://savrn.com/models/dinov3-vitl16-pretrain-lvd1689m) [Camenduru](https://savrn.com/model-publishers/camenduru) DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. These are Vision Transformer and ConvNeXt models trained following the method described in the DINOv3 paper. 12 models are provided: - 10 models pretrained on web data (LVD-1689M dataset) - 1 ViT-7B trained from scratch, - 5 ViT-S/S+/B/L/H+ models distilled from the ViT-7B, - 4 ConvNeXt-{T/S/B/L} models distilled from the ViT-7B, - 2 models… Open weights other 303M parameters transformers [View model](https://savrn.com/models/dinov3-vitl16-pretrain-lvd1689m) Model · Image feature extraction ### [clip-vitb-mini-distilled](https://savrn.com/models/clip-vitb-mini-distilled) [AbstractPhila](https://savrn.com/model-publishers/abstractphil) An 8.66M-parameter ViT image encoder (10.0% of a CLIP-B/16 image tower) producing 512-d embeddings compatible with the text tower. The primary checkpoint was distilled on CC12M (10,968,539 images) against the generalized-Procrustes consensus of five CLIP teachers — never against the deployment teacher — and carries a frozen 512×512 rotation that maps its outputs into the deployment frame, where it outperforms the student distilled directly against that teacher on every task gauge, both seeds (full tables below). The rotation is applied by default (config.applyrotation); pass applyrotation=False to getimagefeatures for the raw consensus-frame embedding. Weights are safetensors; the modeling… Open weights apache-2.0 9M parameters transformers [View model](https://savrn.com/models/clip-vitb-mini-distilled) Model · Image feature extraction ### [I-JEPA-Agro](https://savrn.com/models/i-jepa-agro) [Junior R F Junior](https://savrn.com/model-publishers/joserfjunior) Projeto completo de triagem visual de anomalias em folhas de soja usando como extrator de representações e HeraclitusDB como banco de eventos e vetores. 1. lê um manifesto com fazenda, talhão, safra e cultivar; 2. executa o I-JEPA ViT-G/16 localmente; 3. aplica média aos patch tokens e normalização L2; 4. persiste cada imagem e seu embedding euclidiano no HeraclitusDB; 5. cria um artefato local para avaliação offline; 6. treina uma sonda linear; 7. busca imagens visualmente semelhantes; 8. oferece busca por uma API FastAPI. - Python 3.11+; - HeraclitusDB ativo em 127.0.0.1:7474; - vários GB livres para o checkpoint; - RAM suficiente para um modelo com aproximadamente 1B parâmetros; - GPU é… Open weights mit transformers [View model](https://savrn.com/models/i-jepa-agro) Model · Image feature extraction ### [IM-Animation-Motion-Encoder](https://savrn.com/models/im-animation-motion-encoder) [Fynn](https://savrn.com/model-publishers/rbaerk) IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation This release contains the final locally retained TiTok-based motion encoder implementation and an exported checkpoint. It provides frame-level motion tokens; it does not include the full animation generator or retargeting network. Code and project videos are available in the linked GitHub repository. The encoder was verified with PyTorch 2.7.1 on CPU using the exported BF16 weights. The weight file is 607,017,208 bytes (approximately 579 MiB). Its SHA256 and provenance are in checkpointinfo.json. frames must be RGB, normalized to [0, 1], with shape [N, 3, 256, 256]. The training preprocessing pads… Open weights apache-2.0 [View model](https://savrn.com/models/im-animation-motion-encoder) Model · Image feature extraction ### [keural-vision-encoder-mid](https://savrn.com/models/keural-vision-encoder-mid) [Hika Dalju](https://savrn.com/model-publishers/hikaf143) A 183.5M-parameter image encoder built from scratch — adaptive tokenization, hierarchical concept tokens, and continuous 2D positional encoding. Not a CLIP/ViT fine-tune. Measured at 384×384 with tokenbudget=512, matching training. Accuracy trails same-size peers — see Limitations and Evaluation for why, and for the higher-k retrieval results where the gap closes. The encoder is frozen and used as-is inside a bilingual (English + Korean) Only a projector (8.9M) and LoRA adapters (5.0M) are trained on top; the decoder is Qwen2.5-7B-Instruct. A vision-language model can score respectably while barely using the image, because many questions are answerable from language priors alone. Each… Open weights other 184M parameters transformers [View model](https://savrn.com/models/keural-vision-encoder-mid) Model · Image feature extraction ### [mobile_o_0_5b_visual_components](https://savrn.com/models/mobile-o-0-5b-visual-components) [Xu Lin](https://savrn.com/model-publishers/gatilin) Open weights other 1B parameters pytorch [View model](https://savrn.com/models/mobile-o-0-5b-visual-components) Model · Image feature extraction ### [RK182X-VIT-dinov2_vits14](https://savrn.com/models/rk182x-vit-dinov2-vits14) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 facebookresearch/dinov2 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-dinov2vits14 - 模型显示名称：RK182X-VIT-dinov2vits14 - 源模型：facebookresearch/dinov2 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights apache-2.0 [View model](https://savrn.com/models/rk182x-vit-dinov2-vits14) Model · Image feature extraction ### [RK182X-VIT-dinov3-vitl16-pretrain-lvd1689m](https://savrn.com/models/rk182x-vit-dinov3-vitl16-pretrain-lvd1689m) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 facebook/dinov3-vitl16-pretrain-lvd1689m 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-dinov3-vitl16-pretrain-lvd1689m - 模型显示名称：RK182X-VIT-dinov3-vitl16-pretrain-lvd1689m - 源模型：facebook/dinov3-vitl16-pretrain-lvd1689m - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：DINOv3 License，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights other [View model](https://savrn.com/models/rk182x-vit-dinov3-vitl16-pretrain-lvd1689m) Model · Image feature extraction ### [RK182X-VIT-dinov3-vits16-pretrain-lvd1689m](https://savrn.com/models/rk182x-vit-dinov3-vits16-pretrain-lvd1689m) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 facebook/dinov3-vits16-pretrain-lvd1689m 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-dinov3-vits16-pretrain-lvd1689m - 模型显示名称：RK182X-VIT-dinov3-vits16-pretrain-lvd1689m - 源模型：facebook/dinov3-vits16-pretrain-lvd1689m - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：DINOv3 License，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights other [View model](https://savrn.com/models/rk182x-vit-dinov3-vits16-pretrain-lvd1689m) Model · Image feature extraction ### [RK182X-VIT-siglip-so400m-patch14-384](https://savrn.com/models/rk182x-vit-siglip-so400m-patch14-384) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 google/siglip-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip-so400m-patch14-384 - 源模型：google/siglip-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights apache-2.0 [View model](https://savrn.com/models/rk182x-vit-siglip-so400m-patch14-384) Model · Image feature extraction ### [RK182X-VIT-siglip2-so400m-patch14-384](https://savrn.com/models/rk182x-vit-siglip2-so400m-patch14-384) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 google/siglip2-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip2-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip2-so400m-patch14-384 - 源模型：google/siglip2-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights apache-2.0 [View model](https://savrn.com/models/rk182x-vit-siglip2-so400m-patch14-384) Model · Image feature extraction ### [thermal-mae-vits-pilot](https://savrn.com/models/thermal-mae-vits-pilot) [DHI Technologies, Inc.](https://savrn.com/model-publishers/dhi-technologies) Access requested at publisher other [View model](https://savrn.com/models/thermal-mae-vits-pilot) Model · Image feature extraction ### [vrs-int-gemma4-vision-fp16](https://savrn.com/models/vrs-int-gemma4-vision-fp16) [Park](https://savrn.com/model-publishers/raspie) Open weights apache-2.0 [View model](https://savrn.com/models/vrs-int-gemma4-vision-fp16) ## Questions ### Which Image feature extraction models are most downloaded? By monthly downloads reported by the Hugging Face Hub: dinov2-base (3.1M); dinov2-small (2.7M); vit_small_patch14_dinov2.lvd142m (2.1M). ## Other Tasks - [Text Generation](https://savrn.com/models/tasks/text-generation) 1598 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 598 - [Robotics](https://savrn.com/models/tasks/robotics) 410 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 405 - [Text Classification](https://savrn.com/models/tasks/text-classification) 336 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 239 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 190 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 149 - [Image Classification](https://savrn.com/models/tasks/image-classification) 140 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 105 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 [See all](https://savrn.com/models/tasks)