| 1 | parakeet-tdt-0.6b-v3mlx-community | Speech Recognition | 402.8K | +402.8K | 60 | 627M |
| 2 | bart-large-cnnfacebook | Summarization | 400.6K | +400.6K | 1,628 | 406M |
| 3 | SmolLM2-135MHuggingFaceTB | Text Generation | 400.1K | +400.1K | 237 | 135M |
| 4 | Qwen3.5-35B-A3BQwen | Image Text to Text | 399K | +399K | 1,518 | 36B |
| 5 | Qwen2-VL-7B-Instruct-AWQQwen | Image Text to Text | 396.4K | +396.4K | 48 | 8.3B |
| 6 | SapBERT-from-PubMedBERT-fulltextcambridgeltl | Embeddings | 396.3K | +396.3K | 79 | 109M |
| 7 | owlv2-base-patch16-ensemblegoogle | Zero Shot Object Detection | 394.4K | +394.4K | 129 | 155M |
| 8 | wav2vec2-large-xlsr-53-persianjonatasgrosman | Speech Recognition | 388.9K | +388.9K | 30 | — |
| 9 | deepseek-v4-ggufantirez | Text Generation | 384.3K | +384.3K | 477 | — |
| 10 | LTX-2.5Lightricks | Image To Video | 384.2K | +384.2K | 5,593 | — |
| 11 | multilingual-e5-large-instructintfloat | Embeddings | 383.8K | +383.8K | 642 | 560M |
| 12 | Qwen2.5-VL-7B-Instruct-AWQQwen | Image Text to Text | 382K | +382K | 108 | 8.3B |
| 13 | GLM-OCRzai-org | Image to Text | 381.5K | +381.5K | 2,098 | 1.3B |
| 14 | siglip2-base-patch16-224google | Zero-Shot Image Classification | 379.8K | +379.8K | 142 | 375M |
| 15 | NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4nvidia | Text Generation | 379.4K | +379.4K | 180 | 18.2B |
| 16 | wav2vec2-large-xlsr-53-finnishjonatasgrosman | Speech Recognition | 379.2K | +379.2K | 2 | — |
| 17 | DeepSeek-V3deepseek-ai | Text Generation | 378.1K | +378.1K | 4,343 | 685B |
| 18 | Minimax-h3-Turbolightx2v | Image To Video | 377.9K | +377.9K | 1,017 | — |
| 19 | pythia-6.9bEleutherAI | Text Generation | 377.4K | +377.4K | 66 | 7B |
| 20 | vit-base-patch16-224-in21kgoogle | Image Feature Extraction | 377.3K | +377.3K | 419 | 86.4M |
| 21 | Qwen3.8-Flash-Next-GGUFunsloth | Image Text to Text | 376.3K | +376.3K | 1,089 | — |
| 22 | parakeet-unified-en-0.6b-ggufhandy-computer | Speech Recognition | 375.9K | +375.9K | 9 | — |
| 23 | Qwen3.5-35B-A3B-FP8Qwen | Image Text to Text | 375.2K | +375.2K | 158 | 36B |
| 24 | dots.ocrdots-studio | Image Text to Text | 374.7K | +374.7K | 1,331 | 3B |
| 25 | Ornith-1.0-35Bornith-ai | Text Generation | 372.3K | +372.3K | 506 | 664.9K |
| 26 | vakyansh-wav2vec2-tamil-tam-250Harveenchadha | Speech Recognition | 367.8K | +367.8K | 4 | — |
| 27 | wav2vec2-base-960hfacebook | Speech Recognition | 367.6K | +367.6K | 406 | 94.4M |
| 28 | sdxl-turbostabilityai | Text to Image | 367.2K | +367.2K | 2,632 | 2.6B |
| 29 | whisper-baseopenai | Speech Recognition | 366K | +366K | 291 | 72.6M |
| 30 | vit_small_patch14_dinov2.lvd142mtimm | Image Feature Extraction | 365.5K | +365.5K | 8 | 22.1M |
| 31 | Qwen3.5-122B-A10B-NVFP4nvidia | Text Generation | 364.2K | +364.2K | 54 | 64.6B |
| 32 | DeepSeek-V3-0324deepseek-ai | Text Generation | 363.6K | +363.6K | 3,177 | 685B |
| 33 | gemma-4-12B-itgoogle | Any to Any | 363.4K | +363.4K | 1,622 | 12B |
| 34 | faster-whisper-baseSystran | Speech Recognition | 361.5K | +361.5K | 38 | — |
| 35 | Cosmos3-Edgenvidia | — | 361K | +361K | 213 | 3.9B |
| 36 | llava-1.5-7b-hfllava-hf | Image Text to Text | 359.2K | +359.2K | 376 | 7.1B |
| 37 | Qwen2.5-VL-7B-Instruct-NVFP4nvidia | Text Generation | 356.8K | +356.8K | 16 | 5B |
| 38 | TinyLlama-1.1B-Chat-v1.0TinyLlama | Text Generation | 356.6K | +356.6K | 1,828 | 1.1B |
| 39 | MiniMax-H3-GGUFunsloth | Image Text To Video | 354.6K | +354.6K | 320 | — |
| 40 | wav2vec2-large-xlsr-53-thairesearch | Speech Recognition | 354.4K | +354.4K | 28 | — |
| 41 | faster-whisper-large-v3-turbodropbox-dash | — | 352.7K | +352.7K | 68 | — |
| 42 | multi-qa-mpnet-base-dot-v1sentence-transformers | Sentence Similarity | 351.2K | +351.2K | 194 | 109M |
| 43 | gender-classificationrizvandwiki | Image Classification | 348.5K | +348.5K | 64 | 85.8M |
| 44 | wav2vec2-base-vi-vlsp2020nguyenvulebinh | Speech Recognition | 347.4K | +347.4K | 2 | — |
| 45 | wav2vec2-xls-r-300m-mixedmesolitica | Speech Recognition | 347.1K | +347.1K | 5 | — |
| 46 | Qwen3.8-27B-NVFP4Inferact | Image Text to Text | 346.5K | +346.5K | 20 | 17.6B |
| 47 | Qwen3-Reranker-0.6BQwen | Text Ranking | 344.1K | +344.1K | 405 | 596M |
| 48 | unidepth-v2-vitl14lpiccinelli | — | 343.4K | +343.4K | 50 | 354M |
| 49 | Muse-Glimmer-30B-GGUFmeta-models | Image Text to Text | 343.3K | +343.3K | 351 | — |
| 50 | distilroberta-basedistilbert | Fill Mask | 343.2K | +343.2K | 182 | 82.8M |