HFText Embeddings

sentence-transformers/all-MiniLM-L6-v2

1024-dim vector↓ 251.0M

HFText Embeddings

BAAI/bge-m3

1024-dim vector↓ 36.1M

HFAnomaly Detection

amazon/chronos-2

anomaly score + map↓ 14.8M

HFText Embeddings

BAAI/bge-large-en-v1.5

1024-dim vector↓ 13.4M

HFDepth Estimation

lpiccinelli/unidepth-v2-vitl14

depth map↓ 10.5M

HFSpeaker Diarization

pyannote/speaker-diarization-3.1

speaker segments↓ 9.8M

HFAudio Embeddings

laion/clap-htsat-fused

512-dim vector↓ 8.3M

HFTranscription

openai/whisper-large-v3-turbo

text + timestamps↓ 7.3M

HFText Embeddings

Qwen/Qwen3-Embedding-0.6B

1024-dim vector↓ 6.9M

HFVisual Embeddings

openai/clip-vit-large-patch14

768-dim vector↓ 6.3M

HFScene Captioning

google/gemma-4-E4B-it

text↓ 5.7M

HFSpeaker Diarization

pyannote/wespeaker-voxceleb-resnet34-LM

speaker segments↓ 5.7M

HFSpeaker Diarization

pyannote/speaker-diarization-community-1

speaker segments↓ 5.1M

HFTranscription

distil-whisper/distil-large-v3

text + timestamps↓ 4.8M

HFTranscription

openai/whisper-large-v3

text + timestamps↓ 4.5M

HFTable Extraction

docling-project/docling-models

table JSON↓ 3.8M

HFSpeaker Diarization

speechbrain/spkrec-ecapa-voxceleb

speaker segments↓ 3.4M

HFText Embeddings

Qwen/Qwen3-Embedding-4B

1024-dim vector↓ 3.4M

HFSegmentation

facebook/sam-vit-huge

mask + label↓ 3.2M

HFOCR

stepfun-ai/GOT-OCR-2.0-hf

text + bbox↓ 3.1M

HFOCR

baidu/Unlimited-OCR

text + bbox↓ 2.9M

HFTranscription

Qwen/Qwen3-ASR-0.6B

text + timestamps↓ 2.9M

HFScene Captioning

Qwen/Qwen3-VL-8B-Instruct

text↓ 2.8M

HFText Embeddings

nomic-ai/modernbert-embed-base

1024-dim vector↓ 2.8M

HFScene Captioning

moonshotai/Kimi-K2.6

text↓ 2.7M

HFVisual Embeddings

google/siglip2-giant-opt-patch16-384

768-dim vector↓ 2.6M

HFScene Captioning

google/gemma-4-E2B-it

text↓ 2.4M

HFScene Captioning

Qwen/Qwen3.6-27B

text↓ 2.4M

HFTranscription

mistralai/Voxtral-Mini-4B-Realtime-2602

text + timestamps↓ 2.4M

HFText Embeddings

Qwen/Qwen3-Embedding-8B

1024-dim vector↓ 2.4M

PyTorchSegmentation

facebook/sam3

mask + label↓ 2.3M

PyTorchFace Detection

deepinsight/insightface-retinaface-r50

face embedding↓ 2.2M

HFScene Captioning

google/paligemma2-3b-mix-448

text↓ 1.8M

NeMoTranscription

nvidia/parakeet-ctc-1.1b

text + timestamps↓ 1.7M

HFAudio Embeddings

MIT/ast-finetuned-audioset-10-10-0.4593

512-dim vector↓ 1.7M

HFSegmentation

CIDAS/clipseg-rd64-refined

mask + label↓ 1.7M

HFScene Captioning

OpenGVLab/InternVL3-8B

text↓ 1.6M

HFObject Detection

IDEA-Research/grounding-dino-base

bbox + label↓ 1.5M

NeMoSpeaker Diarization

nvidia/speakerverification_en_titanet_large

speaker segments↓ 1.5M

HFText Embeddings

google/embeddinggemma-300m

1024-dim vector↓ 1.5M

HFText Embeddings

nvidia/NV-Embed-v2

1024-dim vector↓ 1.5M

HFOCR

datalab-to/chandra-ocr-2

text + bbox↓ 1.45M

HFVisual Embeddings

google/siglip-base-patch16-224

768-dim vector↓ 1.4M

HFScene Captioning

Qwen/Qwen3-VL-30B-A3B-Instruct

text↓ 1.4M

HFAudio Embeddings

laion/larger_clap_general

512-dim vector↓ 1.4M

HFText Embeddings

nomic-ai/nomic-embed-text-v2-moe

1024-dim vector↓ 1.4M

HFText Embeddings

Qwen/Qwen3-VL-Embedding-2B

1024-dim vector↓ 1.4M

HFText Embeddings

Qwen/Qwen3-VL-Embedding-8B

1024-dim vector↓ 1.4M

HFVisual Embeddings

nomic-ai/nomic-embed-vision-v1.5

768-dim vector↓ 1.3M

HFAudio Embeddings

microsoft/wavlm-large

512-dim vector↓ 1.3M

HFAudio Embeddings

kyutai/mimi

512-dim vector↓ 1.3M

HFOCR

deepseek-ai/DeepSeek-OCR-2

text + bbox↓ 1.2M

HFText Embeddings

Snowflake/snowflake-arctic-embed-m-v2.0

1024-dim vector↓ 1.2M

HFDocument Structure

microsoft/layoutlmv3-base

structure tokens↓ 1.2M

HFVisual Embeddings

google/siglip2-so400m-patch16-384

768-dim vector↓ 1.1M

PyTorchFace Detection

timesler/facenet-pytorch

face embedding↓ 1.1M

HFScene Captioning

google/gemma-4-26B-A4B-it

text↓ 1.1M

HFDocument Structure

docling-project/docling-layout-heron

structure tokens↓ 1.1M

HFText Embeddings

Snowflake/snowflake-arctic-embed-l-v2.0

1024-dim vector↓ 1.03M

HFScene Captioning

Qwen/Qwen3.8-27B

text↓ 1.0M

HFAnomaly Detection

amazon/chronos-bolt-base

anomaly score + map↓ 980K

HFScene Captioning

LGAI-EXAONE/EXAONE-4.5-33B

text↓ 976K

HFText Embeddings

nomic-ai/modernbert-embed-large

1024-dim vector↓ 890K

HFSegmentation

ZhengPeng7/BiRefNet

mask + label↓ 824K

HFScene Captioning

google/gemma-4-31B-it

text↓ 820K

HFVisual Embeddings

facebook/dinov2-large

768-dim vector↓ 799K

HFAudio Embeddings

laion/clap-htsat-unfused

512-dim vector↓ 792K

HFText Embeddings

sentence-transformers/LaBSE

1024-dim vector↓ 755K

HFOCR

lightonai/LightOnOCR-2-1B

text + bbox↓ 730K

NeMoTranscription

nvidia/parakeet-tdt-0.6b-v3

text + timestamps↓ 730K

HFTable Extraction

microsoft/table-transformer-detection

table JSON↓ 719K

HFSegmentation

briaai/RMBG-2.0

mask + label↓ 717K

HFVisual Embeddings

facebook/dinov3-vitl16-pretrain-lvd1689m

768-dim vector↓ 700K

HFScene Captioning

microsoft/Florence-2-large

text↓ 655K

HFObject Detection

facebook/detr-resnet-50

bbox + label↓ 586K

HFScene Captioning

google/gemma-4-12B-it

text↓ 581K

HFScene Captioning

Qwen/Qwen3-VL-4B-Instruct

text↓ 580K

HFTranscription

facebook/hubert-large-ls960-ft

text + timestamps↓ 579K

HFVisual Embeddings

jinaai/jina-embeddings-v4

768-dim vector↓ 532K

HFTranscription

mistralai/Voxtral-Mini-3B-2507

text + timestamps↓ 532K

HFOCR

zai-org/GLM-OCR

text + bbox↓ 520K

HFDocument Structure

docling-project/SmolDocling-256M-preview

structure tokens↓ 520K

HFDepth Estimation

apple/DepthPro

depth map↓ 520K

HFTranscription

CohereLabs/cohere-transcribe-03-2026

text + timestamps↓ 508K

HFOCR

baidu/Qianfan-OCR

text + bbox↓ 482K

PyTorchVisual Embeddings

facebook/dinov3-large

768-dim vector↓ 450K

HFScene Captioning

OpenGVLab/InternVL3-78B

text↓ 450K

HFScene Captioning

Salesforce/blip2-opt-2.7b

text↓ 448K

HFText Embeddings

ibm-granite/granite-embedding-english-r2

1024-dim vector↓ 420K

HFTranscription

Qwen/Qwen3-ForcedAligner-0.6B

text + timestamps↓ 404K

HFDocument Structure

PaddlePaddle/PP-DocLayoutV3

structure tokens↓ 400K

HFScene Captioning

microsoft/Phi-4-multimodal-instruct

text↓ 391K

HFDocument Structure

fastino/gliner2-base-v1

structure tokens↓ 379K

HFAudio Embeddings

facebook/encodec_24khz

512-dim vector↓ 362K

HFCode Extraction

nomic-ai/nomic-embed-code

code + language↓ 361K

HFVisual Embeddings

Marqo/marqo-fashionSigLIP

768-dim vector↓ 353K

NeMoTranscription

nvidia/parakeet-tdt-1.1b

text + timestamps↓ 350K

HFOCR

nvidia/NVIDIA-Nemotron-Parse-v1.1

text + bbox↓ 343K

HFOCR

tencent/HunyuanOCR

text + bbox↓ 337K

HFSegmentation

briaai/RMBG-1.4

mask + label↓ 333K

HFAudio Embeddings

laion/larger_clap_music_and_speech

512-dim vector↓ 330K

HFAudio Embeddings

m-a-p/MERT-v1-330M

512-dim vector↓ 329K

PyTorchObject Detection

AILab-CVC/YOLO-World-L

bbox + label↓ 320K

HFScene Captioning

microsoft/Phi-4-reasoning-vision-15B

text↓ 320K

HFTranscription

Qwen/Qwen3-ASR-1.7B

text + timestamps↓ 320K

HFScene Captioning

Qwen/Qwen3.6-35B-A3B

text↓ 310K

HFTranscription

facebook/mms-1b-all

text + timestamps↓ 298K

HFVisual Embeddings

facebook/vjepa2-vitl-fpc64-256

768-dim vector↓ 297K

HFTranscription

microsoft/VibeVoice-ASR-HF

text + timestamps↓ 295K

HFOCR

opendatalab/MinerU2.5-Pro-2604-1.2B

text + bbox↓ 283K

HFOCR

rednote-hilab/dots.ocr

text + bbox↓ 281K

HFOCR

microsoft/trocr-large-handwritten

text + bbox↓ 280K

HFScene Captioning

moondream/moondream3-preview

text↓ 276K

HFAudio Embeddings

laion/larger_clap_music

512-dim vector↓ 270K

HFScene Captioning

google/medgemma-27b-it

text↓ 267K

HFScene Captioning

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

text↓ 263K

HFText Embeddings

ibm-granite/granite-embedding-small-english-r2

1024-dim vector↓ 260K

HFTranscription

ibm-granite/granite-speech-4.1-2b

text + timestamps↓ 251K

HFScene Captioning

apple/FastVLM-0.5B

text↓ 240K

HFScene Captioning

HuggingFaceTB/SmolVLM2-2.2B-Instruct

text↓ 238K

HFVisual Embeddings

google/tipsv2-so400m14

768-dim vector↓ 236K

HFScene Captioning

openbmb/MiniCPM-V-4.6

text↓ 222K

HFCode Extraction

microsoft/codebert-base

code + language↓ 221K

HFOCR

reducto/RolmOCR

text + bbox↓ 211K

HFObject Detection

ustc-community/dfine-xlarge-coco

bbox + label↓ 210K

HFOCR

ByteDance/Dolphin-v2

text + bbox↓ 210K

HFTranscription

kyutai/stt-2.6b-en

text + timestamps↓ 210K

HFAudio Embeddings

m-a-p/MERT-v1-95M

512-dim vector↓ 210K

HFText Embeddings

microsoft/harrier-oss-v1-0.6b

1024-dim vector↓ 203K

HFScene Captioning

MiniMaxAI/MiniMax-M3

text↓ 200K

HFOCR

tiiuae/Falcon-OCR

text + bbox↓ 195K

HFSegmentation

ZhengPeng7/BiRefNet_HR

mask + label↓ 190K

HFText Embeddings

jinaai/jina-embeddings-v5-text-small

1024-dim vector↓ 187K

HFObject Detection

PekingU/rtdetr_v2_r101vd

bbox + label↓ 180K

HFFace Detection

fal/AuraFace-v1

face embedding↓ 180K

HFTranscription

usefulsensors/moonshine-streaming-medium

text + timestamps↓ 180K

HFCode Extraction

nomic-ai/CodeRankEmbed

code + language↓ 180K

PyTorchAnomaly Detection

amazon/patchcore-resnet50

anomaly score + map↓ 180K

HFDepth Estimation

facebook/VGGT-1B

depth map↓ 180K

HFScene Captioning

zai-org/GLM-4.5V

text↓ 177K

HFText Embeddings

jinaai/jina-embeddings-v5-text-nano

1024-dim vector↓ 176K

HFText Embeddings

Alibaba-NLP/gte-modernbert-base

1024-dim vector↓ 175K

HFScene Captioning

nvidia/Cosmos-Reason2-2B

text↓ 169K

HFText Embeddings

voyageai/voyage-4-nano

1024-dim vector↓ 168K

HFVisual Embeddings

vidore/colqwen2.5-v0.2

768-dim vector↓ 159K

HFObject Detection

hustvl/yolos-tiny

bbox + label↓ 158K

HFDocument Structure

ibm-granite/granite-docling-258M

structure tokens↓ 150K

HFObject Detection

google/owlv2-large-patch14-ensemble

bbox + label↓ 145K

HFScene Captioning

CohereLabs/command-a-plus-05-2026-bf16

text↓ 145K

HFVisual Embeddings

facebook/vjepa2-vitg-fpc64-256

768-dim vector↓ 140K

HFTable Extraction

microsoft/table-transformer-structure-recognition-v1.1-all

table JSON↓ 138K

HFText Embeddings

codefuse-ai/F2LLM-v2-14B

1024-dim vector↓ 126K

HFDepth Estimation

depth-anything/DA3NESTED-GIANT-LARGE-1.1

depth map↓ 121K

HFVisual Embeddings

facebook/dinov3-convnext-large-pretrain-lvd1689m

768-dim vector↓ 120K

HFTranscription

ibm-granite/granite-4.0-1b-speech

text + timestamps↓ 120K

HFText Embeddings

perplexity-ai/pplx-embed-v1-0.6b

1024-dim vector↓ 120K

HFAnomaly Detection

Salesforce/moirai-2.0-R-small

anomaly score + map↓ 120K

HFText Embeddings

lightonai/GTE-ModernColBERT-v1

1024-dim vector↓ 119K

HFScene Captioning

openbmb/MiniCPM-V-4_5

text↓ 116K

HFScene Captioning

zai-org/GLM-4.6V

text↓ 112K

HFScene Captioning

nvidia/Eagle2.5-8B

text↓ 110K

HFVisual Embeddings

jinaai/jina-embeddings-v5-omni-small-retrieval

768-dim vector↓ 106K

HFScene Captioning

openbmb/MiniCPM-o-4_5

text↓ 100K

HFOCR

nanonets/Nanonets-OCR2-3B

text + bbox↓ 100K

HFScene Captioning

apple/FastVLM-7B

text↓ 98K

HFText Embeddings

zeroentropy/zembed-1-embedding

1024-dim vector↓ 98K

NeMoTranscription

nvidia/canary-1b-v2

text + timestamps↓ 96K

HFObject Detection

nvidia/LocateAnything-3B

bbox + label↓ 95K

HFTranscription

ibm-granite/granite-speech-4.1-2b-plus

text + timestamps↓ 95K

HFAnomaly Detection

google/timesfm-2.5-200m-transformers

anomaly score + map↓ 93K

HFDepth Estimation

depth-anything/DA3-LARGE-1.1

depth map↓ 93K

HFOCR

allenai/olmOCR-2-7B-1025

text + bbox↓ 88K

HFScene Captioning

microsoft/OmniParser-v2.0

text↓ 85K

HFScene Captioning

allenai/Molmo2-8B

text↓ 85K

HFTranscription

facebook/seamless-m4t-v2-large

text + timestamps↓ 85K

HFAnomaly Detection

Maple728/TimeMoE-50M

anomaly score + map↓ 85K

HFSegmentation

facebook/sam2.1-hiera-large

mask + label↓ 79K

HFVisual Embeddings

laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

768-dim vector↓ 77K

HFText Embeddings

ibm-granite/granite-embedding-311m-multilingual-r2

1024-dim vector↓ 77K

HFText Embeddings

ibm-granite/granite-embedding-311m-multilingual-r2

1024-dim vector↓ 77K

HFSegmentation

facebook/sam3.1

mask + label↓ 77K

HFDepth Estimation

depth-anything/Depth-Anything-V2-Large

depth map↓ 75K

HFVisual Embeddings

jinaai/jina-clip-v2

768-dim vector↓ 73K

HFAudio Embeddings

facebook/pe-av-large

512-dim vector↓ 71K

HFOCR

microsoft/trocr-large-printed

text + bbox↓ 65K

NeMoTranscription

nvidia/nemotron-speech-streaming-en-0.6b

text + timestamps↓ 65K

HFCode Extraction

Salesforce/SFR-Embedding-Code-400M_R

code + language↓ 65K

HFTable Extraction

microsoft/table-transformer-structure-recognition-v1.1-pub

table JSON↓ 62K

HFVisual Embeddings

nvidia/llama-nemotron-embed-vl-1b-v2

768-dim vector↓ 60K

HFVisual Embeddings

facebook/PE-Core-G14-448

768-dim vector↓ 58K

HFDocument Structure

naver-clova-ix/donut-base

structure tokens↓ 58K

HFTranscription

CohereLabs/cohere-transcribe-arabic-07-2026

text + timestamps↓ 53K

HFDepth Estimation

depth-anything/DA3-SMALL

depth map↓ 51K

HFScene Captioning

bytedance-research/Vidi-7B

text↓ 48K

HFSpeaker Diarization

Wespeaker/wespeaker-voxceleb-resnet293-LM

speaker segments↓ 48K

HFDepth Estimation

Intel/dpt-large

depth map↓ 46K

HFScene Captioning

ibm-granite/granite-4.0-3b-vision

text↓ 45K

HFScene Captioning

omni-research/Tarsier2-7b-0115

text↓ 45K

HFSegmentation

facebook/EdgeTAM

mask + label↓ 45K

HFVisual Embeddings

facebook/metaclip-2-worldwide-huge-quickgelu

768-dim vector↓ 44K

HFOCR

PaddlePaddle/PaddleOCR-VL-1.6

text + bbox↓ 41K

HFVisual Embeddings

jinaai/jina-embeddings-v5-omni-small

768-dim vector↓ 40K

HFText Embeddings

nvidia/llama-embed-nemotron-8b

1024-dim vector↓ 40K

HFOCR

ibm-granite/granite-vision-4.1-4b

text + bbox↓ 39K

HFScene Captioning

Kwai-Keye/Keye-VL-8B-Preview

text↓ 38K

CosmosScene Captioning

nvidia/Cosmos3-Nano

text↓ 36.7K

HFObject Detection

Roboflow/rf-detr-base

bbox + label↓ 36K

HFScene Captioning

sensenova/SenseNova-U1-8B-MoT

text↓ 32.7K

HFScene Captioning

bytedance-research/Lance

text↓ 32K

HFTranscription

facebook/wav2vec2-large-960h

text + timestamps↓ 32K

HFVisual Embeddings

OpenGVLab/InternVideo2-Stage1-1B-224p-K700

768-dim vector↓ 31K

HFVisual Embeddings

facebook/PE-Spatial-G14-448

768-dim vector↓ 31K

NeMoSpeaker Diarization

nvidia/diar_streaming_sortformer_4spk-v2

speaker segments↓ 30K

HFVisual Embeddings

nvidia/C-RADIOv4-H

768-dim vector↓ 29K

HFCode Extraction

Salesforce/codet5p-110m-embedding

code + language↓ 28K

HFObject Detection

openmmlab-community/mm_grounding_dino_large_all

bbox + label↓ 27.7K

HFFace Detection

Idiap/EdgeFace-S-GAMMA

face embedding↓ 24K

HFVisual Embeddings

TomoroAI/tomoro-colqwen3-embed-4b

768-dim vector↓ 23K

HFText Embeddings

mixedbread-ai/mxbai-colbert-large-v1

1024-dim vector↓ 22K

HFDepth Estimation

yyfz233/Pi3

depth map↓ 22K

HFAnomaly Detection

google/timesfm-2.0-500m-pytorch

anomaly score + map↓ 20.5K

HFVisual Embeddings

BAAI/EVA02-CLIP-L-14-336

768-dim vector↓ 19K

HFScene Captioning

Vision-CAIR/Tempo-6B

text↓ 18K

HFObject Detection

iSEE-Laboratory/llmdet_large

bbox + label↓ 16K

HFText Embeddings

ibm-granite/granite-embedding-97m-multilingual-r2

1024-dim vector↓ 15.6K

HFVisual Embeddings

vidore/colpali-v1.3

768-dim vector↓ 15K

HFVisual Embeddings

facebook/dinov3-vit7b16-pretrain-lvd1689m

768-dim vector↓ 15K

HFScene Captioning

deepseek-ai/deepseek-vl2-small

text↓ 15K

HFOCR

PaddlePaddle/PaddleOCR-VL-1.5

text + bbox↓ 15K

HFScene Captioning

microsoft/Fara-7B

text↓ 13.6K

HFVisual Embeddings

nvidia/omni-embed-nemotron-3b

768-dim vector↓ 13K

PyTorchObject Detection

ultralytics/yolo26n

bbox + label↓ 12K

HFAudio Embeddings

mispeech/dasheng-1.2B

512-dim vector↓ 12K

HFObject Detection

omlab/omdet-turbo-swin-tiny-hf

bbox + label↓ 11.5K

HFScene Captioning

moonshotai/Kimi-VL-A3B-Thinking-2506

text↓ 10.3K

HFObject Detection

google/owlvit-large-patch14

bbox + label↓ 10K

HFDocument Structure

numind/NuExtract3

structure tokens↓ 10K

HFVisual Embeddings

nvidia/C-RADIOv4-SO400M

768-dim vector↓ 9.4K

HFScene Captioning

stepfun-ai/Step-3.7-Flash

text↓ 9.3K

HFText Embeddings

lightonai/Reason-ModernColBERT

1024-dim vector↓ 9.1K

HFVisual Embeddings

vidore/colpali-v1.2

768-dim vector↓ 9K

HFVisual Embeddings

nvidia/nemotron-colembed-vl-8b-v2

768-dim vector↓ 9K

HFCode Extraction

jinaai/jina-code-embeddings-1.5b

code + language↓ 8.9K

HFVisual Embeddings

jinaai/jina-embeddings-v5-omni-nano

768-dim vector↓ 8K

HFVisual Embeddings

BidirLM/BidirLM-Omni-2.5B-Embedding

768-dim vector↓ 8K

HFAudio Embeddings

facebook/encodec_48khz

512-dim vector↓ 7.8K

HFScene Captioning

AIDC-AI/Ovis2.6-30B-A3B

text↓ 7.4K

HFSegmentation

facebook/sam2.1-hiera-base-plus

mask + label↓ 7.3K

HFAnomaly Detection

nvidia/Cosmos-Embed1-448p-anomaly-detection

anomaly score + map↓ 7K

NeMoSpeaker Diarization

nvidia/diar_sortformer_4spk-v1

speaker segments↓ 6.1K

HFVisual Embeddings

VLM2Vec/VLM2Vec-V2.0

768-dim vector↓ 6K

HFText Embeddings

perplexity-ai/pplx-embed-context-v1-4b

1024-dim vector↓ 5.2K

HFText Embeddings

perplexity-ai/pplx-embed-v1-late-0.6b

1024-dim vector↓ 4.9K

HFAudio Embeddings

mtg-upf/discogs-maest-30s-pw-129e

512-dim vector↓ 4.5K

NeMoTranscription

nvidia/nemotron-3.5-asr-streaming-0.6b

text + timestamps↓ 4.2K

HFOCR

FireRedTeam/FireRed-OCR

text + bbox↓ 4.1K

HFObject Detection

Roboflow/rf-detr-large

bbox + label↓ 4K

HFScene Captioning

NemoStation/Marlin-2B

text↓ 4K

HFTranscription

FunAudioLLM/SenseVoiceSmall

text + timestamps↓ 4.0K

HFTable Extraction

foduucom/table-detection-and-extraction

table JSON↓ 3.4K

HFDocument Structure

google/pix2struct-base

structure tokens↓ 3.3K

HFVisual Embeddings

jinaai/jina-embeddings-v5-omni-nano-retrieval

768-dim vector↓ 3K

HFVisual Embeddings

LCO-Embedding/LCO-Embedding-Omni-3B

768-dim vector↓ 3K

HFVisual Embeddings

vidore/colqwen-omni-v0.1

768-dim vector↓ 3K

PyTorchOCR

nvidia/nemotron-ocr-v2

text + bbox↓ 2.9K

HFFace Detection

minchul/cvlface_adaface_ir101_webface12m

face embedding↓ 2.7K

HFVisual Embeddings

LCO-Embedding/LCO-Embedding-Omni-7B

768-dim vector↓ 2.1K

HFVisual Embeddings

google/videoprism-base-f16r288

768-dim vector↓ 2K

HFVisual Embeddings

BAAI/BGE-VL-base

768-dim vector↓ 2K

HFScene Captioning

DAMO-NLP-SG/VideoLLaMA3-7B

text↓ 2K

HFTranscription

XiaomiMiMo/MiMo-V2.5-ASR

text + timestamps↓ 2K

HFText Embeddings

lightonai/Agent-ModernColBERT

1024-dim vector↓ 1.9K

HFCode Extraction

Salesforce/SFR-Embedding-Code-2B_R

code + language↓ 1.5K

HFScene Captioning

yanziang/InternVideo3-8B-Instruct

text↓ 1.4K

NeMoTranscription

nvidia/parakeet-rnnt-1.1b

text + timestamps↓ 1.4K

HFScene Captioning

facebook/Perception-LM-3B

text↓ 1.3K

HFScene Captioning

Hcompany/Holo-3.1-4B

text↓ 1.3K

HFAnomaly Detection

Datadog/Toto-2.0-2.5B

anomaly score + map↓ 1.3K

HFFace Detection

minchul/cvlface_adaface_ir50_ms1mv2

face embedding↓ 1.2K

HFVisual Embeddings

webAI-Official/webAI-ColVec1-4b

768-dim vector↓ 1K

HFObject Detection

Roboflow/rf-detr-medium

bbox + label↓ 1K

HFVisual Embeddings

google/videoprism-large-f8r288

768-dim vector↓ 984

HFScene Captioning

TencentARC/TimeLens-8B

text↓ 968

HFVisual Embeddings

moonshotai/MoonViT-SO-400M

768-dim vector↓ 835

HFVisual Embeddings

Cognitive-Lab/ColNetraEmbed

768-dim vector↓ 685

HFVisual Embeddings

nomic-ai/colnomic-embed-multimodal-7b

768-dim vector↓ 585

HFScene Captioning

ParaVT/ParaVT-8B

text↓ 544

HFVisual Embeddings

nomic-ai/nomic-embed-multimodal-3b

768-dim vector↓ 499

HFVisual Embeddings

apple/aimv2-large-patch14-native

768-dim vector↓ 459

HFVisual Embeddings

tencent/WeMM-Embedding-2B

768-dim vector↓ 424

HFFace Detection

minchul/cvlface_adaface_vit_base_kprpe_webface12m

face embedding↓ 409

HFVisual Embeddings

tencent/WeMM-Embedding-9B

768-dim vector↓ 385

HFScene Captioning

Kwai-Keye/Keye-VL-2.0-30B-A3B

text↓ 290

HFAudio Embeddings

tsinghua-ee/WAVE-7B

512-dim vector↓ 288

HFText Embeddings

Kingsoft-LLM/QZhou-Embedding

1024-dim vector↓ 273

HFVisual Embeddings

Haon-Chen/e5-omni-7B

768-dim vector↓ 261

HFVisual Embeddings

BAAI/BGE-VL-v1.5-zs

768-dim vector↓ 245

HFDocument Structure

microsoft/dit-large

structure tokens↓ 217

HFVisual Embeddings

NCSOFT/GME-VARCO-VISION-Embedding

768-dim vector↓ 214

HFVisual Embeddings

tencent/WeMM-Embedding-4B

768-dim vector↓ 184

HFVisual Embeddings

Alibaba-NLP/GVE-3B

768-dim vector↓ 164

HFVisual Embeddings

nomic-ai/nomic-embed-multimodal-7b

768-dim vector↓ 163

HFObject Detection

fushh7/ObjEmbed-2B

bbox + label↓ 123

HFScene Captioning

nvidia/4D-RGPT-8B

text↓ 108

HFVisual Embeddings

apple/aimv2-3B-patch14-448

768-dim vector↓ 80

HFFace Detection

minchul/cvlface_adaface_vit_base_webface4m

face embedding↓ 65

HFSegmentation

Roboflow/rf-detr-seg-large

mask + label↓ 48

C++/PythonVector Indexing

facebook/faiss

index + results↓ 39.5K★

HFScene Captioning

WorldSeek-AI/WorldSeek-Omni-2B-Preview

text↓ 21

HFVisual Embeddings

FireRedTeam/ReMatch-3B

768-dim vector↓ 14

Gemini APIVisual Embeddings

google/gemini-embedding-2

768-dim vector↓ N/A

HFVisual Embeddings

ahmed-masry/ColMate-3B

768-dim vector↓ N/A

HFVisual Embeddings

ModernVBERT/ColModernVBERT

768-dim vector↓ N/A

PyTorchObject Detection

ultralytics/yolov8n

bbox + label↓ N/A

PyTorchObject Detection

ultralytics/yolo11n

bbox + label↓ -

ONNXFace Detection

immich-app/buffalo_l

face embedding↓ N/A

HFScene Captioning

OpenGVLab/InternVL3_5-8B

text↓ N/A

PyTorchOCR

PaddlePaddle/paddleocr

text + bbox↓ N/A

NeMoTranscription

nvidia/canary-qwen-2.5b

text + timestamps↓ N/A

PyTorchAudio Embeddings

microsoft/BEATs

512-dim vector↓ NEW

HFText Embeddings

lightonai/LateOn-Code

1024-dim vector↓ N/A

PyTorchDocument Structure

nvidia/nemotron-page-elements-v3

structure tokens↓ N/A

PyTorchTable Extraction

poloclub/UniTable

table JSON↓ NEW

PyTorchSegmentation

netflix/void-model

mask + label↓ N/A

C++/PythonVector Indexing

google/scann

index + results↓ -

All Models