| 1 | all-MiniLM-L6-v2sentence-transformers | Sentence Similarity | 256.1M | — | 5,246 | 22.7M |
| 2 | bert-base-uncasedgoogle-bert | Fill Mask | 96.3M | — | 2,739 | 110M |
| 3 | ms-marco-MiniLM-L6-v2cross-encoder | Text Ranking | 87.8M | — | 301 | 22.7M |
| 4 | bge-small-en-v1.5BAAI | Embeddings | 71.9M | — | 538 | 33.4M |
| 5 | electra-base-discriminatorgoogle | — | 55.1M | — | 154 | — |
| 6 | paraphrase-multilingual-MiniLM-L12-v2sentence-transformers | Sentence Similarity | 54.6M | — | 1,353 | 118M |
| 7 | bge-m3BAAI | Sentence Similarity | 36.3M | — | 3,421 | — |
| 8 | chronos-2amazon | Time Series Forecasting | 35.8M | — | 406 | 119M |
| 9 | unidepth-v2-vitl14lpiccinelli | — | 26.9M | — | 50 | 354M |
| 10 | all-mpnet-base-v2sentence-transformers | Sentence Similarity | 25M | — | 1,342 | 109M |
| 11 | Qwen3-0.6BQwen | Text Generation | 24.4M | — | 1,533 | 752M |
| 12 | t5-smallgoogle-t5 | Translation | 22.9M | — | 592 | 60.5M |
| 13 | clip-vit-base-patch32openai | Zero-Shot Image Classification | 20.5M | — | 1,002 | — |
| 14 | mobilenetv3_small_100.lamb_in1ktimm | Image Classification | 19.2M | — | 101 | 2.6M |
| 15 | xlm-roberta-baseFacebookAI | Fill Mask | 18.6M | — | 885 | 279M |
| 16 | bge-reranker-v2-m3BAAI | Text Classification | 18.6M | — | 1,142 | 568M |
| 17 | MiniMax-H3Comfy-Org | — | 17.3M | — | 1,508 | — |
| 18 | nomic-embed-text-v1.5nomic-ai | Sentence Similarity | 16.5M | — | 893 | 137M |
| 19 | tiny-Qwen2ForCausalLM-2.5trl-internal-testing | Text Generation | 15.8M | — | 20 | 2.4M |
| 20 | Qwen3-8BQwen | Text Generation | 15.1M | — | 1,316 | 8.2B |
| 21 | opt-125mfacebook | Text Generation | 15M | — | 293 | — |
| 22 | gpt2openai-community | Text Generation | 14.2M | — | 3,412 | 137M |
| 23 | Qwen3.5-9BQwen | Image Text to Text | 13.6M | — | 1,849 | 9.7B |
| 24 | bge-large-en-v1.5BAAI | Embeddings | 13.5M | — | 715 | 335M |
| 25 | Qwen3.6-35B-A3B-FP8Qwen | Image Text to Text | 13.1M | — | 357 | 36B |
| 26 | Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth | Text Generation | 12.7M | — | 917 | — |
| 27 | Qwen3.6-35B-A3B-NVFP4nvidia | Text Generation | 12.6M | — | 564 | 18.7B |
| 28 | multilingual-e5-smallintfloat | Sentence Similarity | 12.4M | — | 392 | 118M |
| 29 | Kokoro-82Mhexgrad | Text to Speech | 12.3M | — | 6,742 | — |
| 30 | bge-base-en-v1.5BAAI | Embeddings | 11.9M | — | 464 | 109M |
| 31 | Qwen2.5-7B-InstructQwen | Text Generation | 11.6M | — | 1,553 | 7.6B |
| 32 | roberta-baseFacebookAI | Fill Mask | 11.2M | — | 638 | 125M |
| 33 | whisperkit-coremlargmaxinc | Speech Recognition | 11M | — | 201 | — |
| 34 | stable-diffusion-v1-5-archiveComfy-Org | — | 10.5M | — | 117 | — |
| 35 | roberta-largeFacebookAI | Fill Mask | 10.4M | — | 319 | 355M |
| 36 | paraphrase-multilingual-mpnet-base-v2sentence-transformers | Sentence Similarity | 10.4M | — | 489 | 278M |
| 37 | adetailerBingsu | — | 10.1M | — | 762 | — |
| 38 | speaker-diarization-3.1pyannote | Speech Recognition | 9.9M | — | 3,153 | — |
| 39 | Qwen3.6-27B-FP8Qwen | Image Text to Text | 9.1M | — | 347 | 27.8B |
| 40 | Qwen2.5-VL-7B-InstructQwen | Image Text to Text | 9M | — | 1,684 | 8.3B |
| 41 | gemma-4-26B-A4B-itgoogle | Image Text to Text | 9M | — | 1,428 | 25.8B |
| 42 | Qwen2.5-1.5B-InstructQwen | Text Generation | 9M | — | 806 | 1.5B |
| 43 | gemma-4-31B-itgoogle | Image Text to Text | 8.8M | — | 3,623 | 31.3B |
| 44 | wav2vec2-large-xlsr-53-japanesejonatasgrosman | Speech Recognition | 8.4M | — | 62 | — |
| 45 | XTTS-v2coqui | Text to Speech | 8.4M | — | 3,743 | — |
| 46 | chronos-bolt-smallautogluon | Time Series Forecasting | 8.2M | — | 61 | 47.7M |
| 47 | contrieverfacebook | — | 8M | — | 96 | — |
| 48 | ms-marco-MiniLM-L4-v2cross-encoder | Text Ranking | 8M | — | 28 | 19.2M |
| 49 | clap-htsat-fusedlaion | Audio Classification | 7.8M | — | 126 | 154M |
| 50 | whisper-large-v3-turboopenai | Speech Recognition | 7.7M | — | 3,260 | 809M |