| 1 | stanford-deidentifier-baseStanfordAIMI | Token Classification | 342.9K | +342.9K | 85 | — |
| 2 | clap-htsat-unfusedlaion | Embeddings | 342.9K | +342.9K | 80 | — |
| 3 | bge-small-en-v1.5-onnx-QQdrant | Sentence Similarity | 341.6K | +341.6K | 3 | — |
| 4 | Unlimited-OCRbaidu | Image Text to Text | 341.6K | +341.6K | 4,315 | 3.3B |
| 5 | gpt2-largeopenai-community | Text Generation | 341.3K | +341.3K | 361 | 812M |
| 6 | Qwen3-VL-Embedding-2BQwen | Sentence Similarity | 340.9K | +340.9K | 461 | 2.1B |
| 7 | parrot_paraphraser_on_T5prithivida | — | 338.4K | +338.4K | 161 | — |
| 8 | CLIP-convnext_base_w-laion2B-s13B-b82K-augreglaion | Zero-Shot Image Classification | 337K | +337K | 9 | — |
| 9 | tiny-Qwen2ForSequenceClassification-2.5trl-internal-testing | Text Classification | 337K | +337K | 1 | 2.4M |
| 10 | gemma-4-E2B-it-litert-lmlitert-community | — | 335K | +335K | 452 | — |
| 11 | Wav2Vec2-large-xlsr-hinditheainerd | Speech Recognition | 331.3K | +331.3K | 13 | 316M |
| 12 | WanVideo_comfyKijai | — | 330.2K | +330.2K | 2,517 | — |
| 13 | OmniVoicek2-fsa | Text to Speech | 329.5K | +329.5K | 1,452 | 613M |
| 14 | blip-image-captioning-baseSalesforce | Image to Text | 328.9K | +328.9K | 894 | — |
| 15 | e5-large-v2intfloat | Sentence Similarity | 327.6K | +327.6K | 283 | 335M |
| 16 | gemma-3-27b-it-int4-awqgaunernst | Image Text to Text | 327.1K | +327.1K | 40 | 27.4B |
| 17 | whisper-tinyXenova | Speech Recognition | 326.7K | +326.7K | 13 | — |
| 18 | yolo-world-mirrorBingsu | — | 325K | +325K | 6 | — |
| 19 | gemma-3-4b-itgoogle | Image Text to Text | 324.3K | +324.3K | 1,540 | 4.3B |
| 20 | chronos-t5-smallamazon | Time Series Forecasting | 324.1K | +324.1K | 143 | 46.2M |
| 21 | tiny-gpt2sshleifer | Text Generation | 322.9K | +322.9K | 36 | — |
| 22 | timesfm-2.5-200m-pytorchgoogle | Time Series Forecasting | 320K | +320K | 267 | 231M |
| 23 | Qwen2-VL-2B-InstructQwen | Image Text to Text | 318.9K | +318.9K | 520 | 2.2B |
| 24 | stable-diffusion-v1-5-archiveComfy-Org | — | 318.7K | +318.7K | 166 | — |
| 25 | pythia-70m-dedupedEleutherAI | Text Generation | 318.5K | +318.5K | 30 | 95.6M |
| 26 | paraphrase-MiniLM-L6-v2sentence-transformers | Sentence Similarity | 318.3K | +318.3K | 150 | 22.7M |
| 27 | nb-wav2vec2-1b-bokmaal-v2NbAiLab | Speech Recognition | 316K | +316K | 0 | 963M |
| 28 | Qwen3.6-35B-A3B-NVFP4RedHatAI | Image Text to Text | 314.9K | +314.9K | 175 | 34.7B |
| 29 | siglip2-giant-opt-patch16-384google | Zero-Shot Image Classification | 314.5K | +314.5K | 45 | 1.9B |
| 30 | colbertv2.0colbert-ir | — | 314.3K | +314.3K | 366 | 110M |
| 31 | Qwen3.8-27B-GGUFlmstudio-community | — | 313.9K | +313.9K | 57 | — |
| 32 | Unlimited-OCR-AWQsahilchachra | Image Text to Text | 313.2K | +313.2K | 3 | 3.4B |
| 33 | Qwen3-VL-Embedding-8BQwen | Sentence Similarity | 311.7K | +311.7K | 485 | 8.1B |
| 34 | clip-vit-base-patch16openai | Zero-Shot Image Classification | 310.4K | +310.4K | 167 | — |
| 35 | SmolVLM2-500M-Video-InstructHuggingFaceTB | Image Text to Text | 310K | +310K | 180 | 507M |
| 36 | Ternary-Bonsai-27B-mlx-2bitprism-ml | Text Generation | 309.4K | +309.4K | 201 | 27.4B |
| 37 | esmfold_v1facebook | — | 308.8K | +308.8K | 55 | — |
| 38 | wav2vec2-xls-r-300m-ftspeechsaattrupdan | Speech Recognition | 307.2K | +307.2K | 0 | 315M |
| 39 | siglip-so400m-patch14-384google | Zero-Shot Image Classification | 306.8K | +306.8K | 691 | 878M |
| 40 | Qwen3.5-9B-GGUFunsloth | Image Text to Text | 305.3K | +305.3K | 954 | — |
| 41 | Bonsai-27B-mlx-1bitprism-ml | Text Generation | 304.5K | +304.5K | 260 | 1.7B |
| 42 | Kimi-K3moonshotai | Image Text to Text | 304.3K | +304.3K | 11.6K | 2.8T |
| 43 | Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF0bserverx | Text Generation | 304.2K | +304.2K | 587 | — |
| 44 | dinov2-largefacebook | Image Feature Extraction | 304.1K | +304.1K | 119 | 304M |
| 45 | bge-micro-v2TaylorAI | Sentence Similarity | 301.6K | +301.6K | 65 | 17.4M |
| 46 | Qwen3.6-35B-A3B-GGUFunsloth | Image Text to Text | 301.1K | +301.1K | 1,645 | — |
| 47 | flux2-devComfy-Org | — | 301K | +301K | 336 | — |
| 48 | turn-detectorlivekit | Text Classification | 299.5K | +299.5K | 150 | 135M |
| 49 | OpenELM-1_1B-Instructapple | Text Generation | 298.6K | +298.6K | 77 | 1.1B |
| 50 | grounding-dino-baseIDEA-Research | Zero Shot Object Detection | 297.5K | +297.5K | 211 | 233M |