| 1 | all-MiniLM-L6-v2sentence-transformers | Sentence Similarity | 59.9M | +59.9M | 6,222 | 22.7M |
| 2 | ms-marco-MiniLM-L6-v2cross-encoder | Text Ranking | 21.2M | +21.2M | 361 | 22.7M |
| 3 | bge-small-en-v1.5BAAI | Embeddings | 15.5M | +15.5M | 602 | 33.4M |
| 4 | bert-base-uncasedgoogle-bert | Fill Mask | 11.9M | +11.9M | 3,397 | 110M |
| 5 | paraphrase-multilingual-MiniLM-L12-v2sentence-transformers | Sentence Similarity | 11.3M | +11.3M | 1,424 | 118M |
| 6 | Qwen3-0.6BQwen | Text Generation | 9.2M | +9.2M | 1,756 | 752M |
| 7 | bge-m3BAAI | Sentence Similarity | 8.9M | +8.9M | 3,835 | — |
| 8 | mobilenetv3_small_100.lamb_in1ktimm | Image Classification | 5.9M | +5.9M | 127 | 2.6M |
| 9 | t5-smallgoogle-t5 | Translation | 5.8M | +5.8M | 655 | 60.5M |
| 10 | chronos-2amazon | Time Series Forecasting | 5.7M | +5.7M | 510 | 119M |
| 11 | clip-vit-base-patch32openai | Zero-Shot Image Classification | 5.5M | +5.5M | 1,581 | — |
| 12 | MiniMax-H3Comfy-Org | — | 5.4M | +5.4M | 2,182 | — |
| 13 | xlm-roberta-baseFacebookAI | Fill Mask | 4.7M | +4.7M | 930 | 279M |
| 14 | all-mpnet-base-v2sentence-transformers | Sentence Similarity | 4.6M | +4.6M | 1,381 | 109M |
| 15 | Qwen3-VL-8B-InstructQwen | Image Text to Text | 4.3M | +4.3M | 1,172 | 8.8B |
| 16 | bge-reranker-v2-m3BAAI | Text Classification | 4M | +4M | 1,227 | 568M |
| 17 | wav2vec2-large-xlsr-53-japanesejonatasgrosman | Speech Recognition | 4M | +4M | 89 | — |
| 18 | gpt2openai-community | Text Generation | 3.8M | +3.8M | 4,217 | 137M |
| 19 | electra-base-discriminatorgoogle | — | 3.5M | +3.5M | 192 | — |
| 20 | Krea-2Comfy-Org | — | 3M | +3M | 654 | — |
| 21 | Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth | Text Generation | 2.9M | +2.9M | 1,121 | — |
| 22 | gemma-4-26B-A4B-itgoogle | Image Text to Text | 2.9M | +2.9M | 1,613 | 25.8B |
| 23 | multilingual-e5-smallintfloat | Sentence Similarity | 2.9M | +2.9M | 442 | 118M |
| 24 | Kokoro-82Mhexgrad | Text to Speech | 2.9M | +2.9M | 7,169 | — |
| 25 | Qwen3.5-9BQwen | Image Text to Text | 2.8M | +2.8M | 2,123 | 9.7B |
| 26 | nomic-embed-text-v1.5nomic-ai | Sentence Similarity | 2.8M | +2.8M | 949 | 137M |
| 27 | whisperkit-coremlargmaxinc | Speech Recognition | 2.7M | +2.7M | 237 | — |
| 28 | paraphrase-multilingual-mpnet-base-v2sentence-transformers | Sentence Similarity | 2.7M | +2.7M | 531 | 278M |
| 29 | Qwen3-8BQwen | Text Generation | 2.6M | +2.6M | 2,082 | 8.2B |
| 30 | locate-anything.cpp-ggufmudler | Object Detection | 2.5M | +2.5M | 24 | — |
| 31 | tiny-Qwen2ForCausalLM-2.5trl-internal-testing | Text Generation | 2.4M | +2.4M | 56 | 2.4M |
| 32 | adetailerBingsu | — | 2.4M | +2.4M | 799 | — |
| 33 | gemma-4-31B-itgoogle | Image Text to Text | 2.3M | +2.3M | 4,058 | 31.3B |
| 34 | bge-large-en-v1.5BAAI | Embeddings | 2.3M | +2.3M | 750 | 335M |
| 35 | bge-base-en-v1.5BAAI | Embeddings | 2.2M | +2.2M | 508 | 109M |
| 36 | Qwen3-Embedding-0.6BQwen | Embeddings | 2.2M | +2.2M | 1,265 | 596M |
| 37 | vit-base-patch16-224google | Image Classification | 2.2M | +2.2M | 1,012 | 86.6M |
| 38 | Qwen2.5-1.5B-InstructQwen | Text Generation | 2.2M | +2.2M | 869 | 1.5B |
| 39 | Llama-3.2-1B-Instructmeta-llama | Text Generation | 2.1M | +2.1M | 1,802 | 1.2B |
| 40 | distilbert-base-uncaseddistilbert | Fill Mask | 2.1M | +2.1M | 1,474 | 67M |
| 41 | roberta-baseFacebookAI | Fill Mask | 2.1M | +2.1M | 668 | 125M |
| 42 | Qwen3-4BQwen | Text Generation | 2M | +2M | 726 | 4B |
| 43 | z_image_turboComfy-Org | — | 2M | +2M | 939 | — |
| 44 | contrieverfacebook | — | 2M | +2M | 123 | — |
| 45 | clap-htsat-fusedlaion | Audio Classification | 2M | +2M | 151 | 154M |
| 46 | Qwen2.5-7B-InstructQwen | Text Generation | 1.9M | +1.9M | 2,416 | 7.6B |
| 47 | multilingual-e5-baseintfloat | Sentence Similarity | 1.9M | +1.9M | 393 | 278M |
| 48 | Qwen2.5-0.5B-InstructQwen | Text Generation | 1.9M | +1.9M | 660 | 494M |
| 49 | multilingual-e5-largeintfloat | Embeddings | 1.9M | +1.9M | 1,261 | 560M |
| 50 | speaker-diarization-3.1pyannote | Speech Recognition | 1.8M | +1.8M | 4,225 | — |