| 1 | DeepSeek-OCRdeepseek-ai | Image Text to Text | 497.2K | +497.2K | 3,391 | 3.3B |
| 2 | LaBSEsetu4993 | Sentence Similarity | 496.8K | +496.8K | 54 | 471M |
| 3 | wav2vec2-large-xlsr-53-teluguanuragshas | Speech Recognition | 492.8K | +492.8K | 5 | — |
| 4 | romanian-wav2vec2gigant | Speech Recognition | 492.8K | +492.8K | 8 | 315M |
| 5 | Laguna-XS-2.1-APEX-GGUFmudler | — | 488.5K | +488.5K | 15 | — |
| 6 | chandra-ocr-2datalab-to | Image Text to Text | 487.3K | +487.3K | 541 | 5.3B |
| 7 | Tiel-Coder-35B-A3B-GGUF-MTPpeculiar-ragdoll | Image Text to Text | 485.6K | +485.6K | 256 | — |
| 8 | Gemma-4-E4B-Uncensored-HauhauCS-AggressiveHauhauCS | Image Text to Text | 479.2K | +479.2K | 1,333 | — |
| 9 | distilgpt2distilbert | Text Generation | 477.8K | +477.8K | 648 | 88.2M |
| 10 | Qwen2.5-14B-Instruct-AWQQwen | Text Generation | 475.9K | +475.9K | 39 | 14.8B |
| 11 | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFDavidAU | Image Text to Text | 473K | +473K | 1,564 | — |
| 12 | Qwen3.8-27B-GSQ-RCO-GGUFISTA-DASLab | Image Text to Text | 472.7K | +472.7K | 2,060 | — |
| 13 | Qwen3.6-27BQwen | Image Text to Text | 469.6K | +469.6K | 2,320 | 27.8B |
| 14 | gte-multilingual-baseAlibaba-NLP | Sentence Similarity | 467.2K | +467.2K | 379 | 305M |
| 15 | musicgen-mediumfacebook | Text to Audio | 463.2K | +463.2K | 170 | — |
| 16 | Gemma-4-31B-IT-NVFP4nvidia | Text Generation | 462.8K | +462.8K | 577 | 20.9B |
| 17 | wav2vec2-large-xlsr-53-chinese-zh-cnjonatasgrosman | Speech Recognition | 462.6K | +462.6K | 136 | — |
| 18 | Llama-3.2-3B-Instructmeta-llama | Text Generation | 462.5K | +462.5K | 2,756 | 3.2B |
| 19 | Qwen3-30B-A3BQwen | Text Generation | 461.8K | +461.8K | 955 | 30.5B |
| 20 | w2v-bert-2.0facebook | Embeddings | 460.6K | +460.6K | 235 | 580M |
| 21 | GLM-4.7-Flashzai-org | Text Generation | 454.4K | +454.4K | 1,864 | 31.2B |
| 22 | filipino-wav2vec2-l-xls-r-300m-officialKhalsuu | Speech Recognition | 452.1K | +452.1K | 2 | — |
| 23 | stsb-bert-tiny-safetensorssentence-transformers-testing | Sentence Similarity | 450.7K | +450.7K | 4 | 4.4M |
| 24 | Qwen3-Reranker-4BQwen | Text Ranking | 449.3K | +449.3K | 165 | 4B |
| 25 | SmolLM2-135M-InstructHuggingFaceTB | Text Generation | 445.8K | +445.8K | 433 | 135M |
| 26 | t5-basegoogle-t5 | Translation | 445.7K | +445.7K | 793 | 223M |
| 27 | wav2vec2-large-xls-r-300m-Urdukingabzpro | Speech Recognition | 445.6K | +445.6K | 15 | 315M |
| 28 | bge-base-enBAAI | Embeddings | 445.4K | +445.4K | 62 | 109M |
| 29 | Qwen2.5-Coder-7B-InstructQwen | Text Generation | 444.5K | +444.5K | 817 | 7.6B |
| 30 | bert-base-multilingual-casedgoogle-bert | Fill Mask | 444.5K | +444.5K | 607 | 179M |
| 31 | nemotron-3.5-asr-streaming-0.6b-ggufhandy-computer | Speech Recognition | 443.8K | +443.8K | 12 | — |
| 32 | nsfw_image_detectionFalconsai | Image Classification | 442.9K | +442.9K | 1,199 | 85.8M |
| 33 | wav2vec2-large-voxrex-swedishKBLab | Speech Recognition | 439.7K | +439.7K | 14 | 315M |
| 34 | docling-layout-herondocling-project | — | 438.3K | +438.3K | 59 | 42.9M |
| 35 | resnet50.a1_in1ktimm | Image Classification | 437.3K | +437.3K | 44 | 25.6M |
| 36 | ms-marco-MiniLM-L12-v2cross-encoder | Text Ranking | 433.8K | +433.8K | 112 | 33.4M |
| 37 | mxbai-embed-large-v1mixedbread-ai | Embeddings | 433K | +433K | 826 | 335M |
| 38 | Qwen3.5-27BQwen | Image Text to Text | 431.5K | +431.5K | 1,058 | 27.8B |
| 39 | clip-vit-large-patch14-336openai | Zero-Shot Image Classification | 429.8K | +429.8K | 311 | — |
| 40 | Qwen2.5-14B-InstructQwen | Text Generation | 428K | +428K | 371 | 14.8B |
| 41 | Qwen-Image-Edit_ComfyUIComfy-Org | — | 426.2K | +426.2K | 499 | — |
| 42 | Ornith-1.0-35B-GGUFornith-ai | Text Generation | 423.1K | +423.1K | 1,053 | — |
| 43 | chatterboxResembleAI | Text to Speech | 418K | +418K | 1,825 | — |
| 44 | siglip-base-patch16-224google | Zero-Shot Image Classification | 417.5K | +417.5K | 92 | 203M |
| 45 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8nvidia | Any to Any | 416.9K | +416.9K | 66 | 33B |
| 46 | Octen-Embedding-8BOcten | Sentence Similarity | 416.8K | +416.8K | 193 | 7.6B |
| 47 | Qwen2.5-0.5BQwen | Text Generation | 416.3K | +416.3K | 463 | 494M |
| 48 | bert-base-NERdslim | Token Classification | 413.3K | +413.3K | 739 | 108M |
| 49 | Dirk-Qwen3.8-27B-GGUFpeculiar-ragdoll | Image Text to Text | 410.8K | +410.8K | 224 | — |
| 50 | Mistral-7B-Instruct-v0.2mistralai | Text Generation | 408K | +408K | 3,241 | 7.2B |