| 1 | Qwen3-ASR-0.6BQwen | Speech Recognition | 4.1M | — | 338 | 938M |
| 2 | MiniMax-H3MiniMaxAI | Image Text To Video | 4M | — | 4,378 | 33.1B |
| 3 | Qwen3-Embedding-4BQwen | Embeddings | 4M | — | 312 | 4B |
| 4 | t5-basegoogle-t5 | Translation | 4M | — | 787 | 223M |
| 5 | Qwen3-VL-4B-InstructQwen | Image Text to Text | 3.9M | — | 448 | 4.4B |
| 6 | nsfw_image_detectionFalconsai | Image Classification | 3.9M | — | 1,168 | 85.8M |
| 7 | wav2vec2-large-xlsr-53-russianjonatasgrosman | Speech Recognition | 3.9M | — | 76 | — |
| 8 | all-MiniLM-L12-v2sentence-transformers | Sentence Similarity | 3.8M | — | 326 | 33.4M |
| 9 | Qwen3.6-27B-NVFP4unsloth | Image Text to Text | 3.8M | — | 276 | 21.2B |
| 10 | Qwen3-32BQwen | Text Generation | 3.6M | — | 737 | 32.8B |
| 11 | gemma-4-E2B-itgoogle | Any to Any | 3.6M | — | 916 | 5.1B |
| 12 | distilbert-base-uncased-finetuned-sst-2-englishdistilbert | Text Classification | 3.6M | — | 943 | 67M |
| 13 | mxbai-embed-large-v1mixedbread-ai | Embeddings | 3.6M | — | 823 | 335M |
| 14 | bert-base-casedgoogle-bert | Fill Mask | 3.6M | — | 370 | 109M |
| 15 | Ornith-1.0-35B-GGUFornith-ai | Text Generation | 3.5M | — | 1,052 | — |
| 16 | pythia-160mEleutherAI | Text Generation | 3.5M | — | 45 | 213M |
| 17 | bge-reranker-baseBAAI | Text Classification | 3.5M | — | 242 | 278M |
| 18 | Mistral-7B-Instruct-v0.3mistralai | — | 3.4M | — | 2,826 | 7.2B |
| 19 | Qwen3-4B-Instruct-2507Qwen | Text Generation | 3.4M | — | 931 | 4B |
| 20 | CLIP-ViT-B-32-laion2B-s34B-b79Klaion | Zero-Shot Image Classification | 3.4M | — | 141 | 151M |
| 21 | gemma-4-12B-itgoogle | Any to Any | 3.3M | — | 1,482 | 12B |
| 22 | wav2vec2-basefacebook | — | 3.3M | — | 124 | — |
| 23 | bart-large-mnlifacebook | Zero-Shot Classification | 3.2M | — | 1,597 | 407M |
| 24 | Ornith-1.0-35Bornith-ai | Text Generation | 3.2M | — | 505 | 664.9K |
| 25 | vitpose-plus-baseusyd-community | Keypoint Detection | 3.1M | — | 33 | 125M |
| 26 | Unlimited-OCRbaidu | Image Text to Text | 3.1M | — | 4,117 | 3.3B |
| 27 | Qwen3-TTS-12Hz-1.7B-BaseQwen | — | 3.1M | — | 491 | 1.9B |
| 28 | Qwen3.5-2BQwen | Image Text to Text | 3.1M | — | 372 | 2.3B |
| 29 | DeepSeek-V4-Flash-0731deepseek-ai | Text Generation | 3.1M | — | 3,652 | 304B |
| 30 | twitter-roberta-base-sentiment-latestcardiffnlp | Text Classification | 3.1M | — | 827 | — |
| 31 | vocos-mel-24khzcharactr | — | 3.1M | — | 42 | — |
| 32 | clip-vit-large-patch14-336openai | Zero-Shot Image Classification | 3M | — | 308 | — |
| 33 | wav2vec2-large-xlsr-53-polishjonatasgrosman | Speech Recognition | 3M | — | 12 | — |
| 34 | deberta-v3-basemicrosoft | Fill Mask | 2.9M | — | 434 | — |
| 35 | Kimi-K3-DSparkRadixArk | Text Generation | 2.9M | — | 54 | 2.2B |
| 36 | Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFDavidAU | Image Text to Text | 2.9M | — | 2,212 | — |
| 37 | jina-embeddings-v3jinaai | Embeddings | 2.8M | — | 1,153 | 572M |
| 38 | chronos-bolt-tinyautogluon | Time Series Forecasting | 2.8M | — | 13 | 8.7M |
| 39 | inclusively-reformulation-it5E-MIMIC | — | 2.8M | — | 2 | 783M |
| 40 | Qwen2.5-14B-InstructQwen | Text Generation | 2.8M | — | 360 | 14.8B |
| 41 | GLM-OCRzai-org | Image Text to Text | 2.8M | — | 1,997 | 1.3B |
| 42 | Florence-2-basemicrosoft | Image Text to Text | 2.8M | — | 393 | 232M |
| 43 | whisper-smallopenai | Speech Recognition | 2.8M | — | 585 | 242M |
| 44 | paraphrase-MiniLM-L6-v2sentence-transformers | Sentence Similarity | 2.8M | — | 150 | 22.7M |
| 45 | Qwen3-Embedding-8BQwen | Embeddings | 2.8M | — | 781 | 7.6B |
| 46 | Kimi-K3moonshotai | Image Text to Text | 2.7M | — | 11K | 2.8T |
| 47 | Qwen3.5-0.8BQwen | Image Text to Text | 2.7M | — | 674 | 873M |
| 48 | chandra-ocr-2datalab-to | Image Text to Text | 2.7M | — | 480 | 5.3B |
| 49 | Qwen3.5-27BQwen | Image Text to Text | 2.7M | — | 1,031 | 27.8B |
| 50 | Qwen3-Reranker-4BQwen | Text Ranking | 2.7M | — | 153 | 4B |