| 1 | xlm-roberta-largeFacebookAI | Fill Mask | 661.4K | +661.4K | 540 | 561M |
| 2 | Qwen-Image_ComfyUIComfy-Org | — | 658.3K | +658.3K | 515 | — |
| 3 | mmarco-mMiniLMv2-L12-H384-v1cross-encoder | Text Ranking | 651.4K | +651.4K | 83 | 118M |
| 4 | wav2vec2-basefacebook | — | 643.3K | +643.3K | 130 | — |
| 5 | Ornith-1.0-9B-GGUFornith-ai | Text Generation | 643.2K | +643.2K | 675 | — |
| 6 | wav2vec2-large-xlsr-53-greekjonatasgrosman | Speech Recognition | 637.5K | +637.5K | 5 | — |
| 7 | sam3facebook | Mask Generation | 633.4K | +633.4K | 3,883 | 860M |
| 8 | wav2vec2-large-xlsr-53-hungarianjonatasgrosman | Speech Recognition | 632.9K | +632.9K | 10 | — |
| 9 | fashion-clippatrickjohncyh | Zero-Shot Image Classification | 629.3K | +629.3K | 294 | 151M |
| 10 | roberta-base-go_emotionsSamLowe | Text Classification | 627K | +627K | 694 | 125M |
| 11 | Qwen3-VL-2B-InstructQwen | Image Text to Text | 614.6K | +614.6K | 483 | 2.1B |
| 12 | dinov2-smallfacebook | Image Feature Extraction | 614.2K | +614.2K | 77 | 22.1M |
| 13 | faster-whisper-tinySystran | Speech Recognition | 605.8K | +605.8K | 28 | — |
| 14 | bart-large-mnlifacebook | Zero-Shot Classification | 602.3K | +602.3K | 1,622 | 407M |
| 15 | vocos-mel-24khzcharactr | — | 600.4K | +600.4K | 43 | — |
| 16 | bge-base-en-v1.5Xenova | Embeddings | 599.4K | +599.4K | 10 | — |
| 17 | Qwen3-8B-AWQQwen | Text Generation | 585.6K | +585.6K | 55 | 8.2B |
| 18 | TRELLIS-image-largemicrosoft | Image To 3d | 584.8K | +584.8K | 692 | — |
| 19 | wav2vec2-large-robust-24-ft-age-genderaudeering | Audio Classification | 580.9K | +580.9K | 63 | 318M |
| 20 | chronos-2-smallautogluon | Time Series Forecasting | 579.7K | +579.7K | 8 | 27.9M |
| 21 | Qwen2.5-VL-3B-InstructQwen | Image Text to Text | 579.1K | +579.1K | 711 | 3.8B |
| 22 | Qwen3.6-27B-FP8Qwen | Image Text to Text | 578.7K | +578.7K | 361 | 27.8B |
| 23 | Qwen2.5-Coder-14B-InstructQwen | Text Generation | 572.3K | +572.3K | 193 | 14.8B |
| 24 | resnet18.a1_in1ktimm | Image Classification | 564.5K | +564.5K | 15 | 11.7M |
| 25 | Qwen3-VL-8B-Instruct-FP8Qwen | Image Text to Text | 560.5K | +560.5K | 84 | 8.8B |
| 26 | Kronos-Tokenizer-baseNeoQuasar | Time Series Forecasting | 559.5K | +559.5K | 80 | 4M |
| 27 | Qwen2.5-32B-InstructQwen | Text Generation | 556.4K | +556.4K | 362 | 32.8B |
| 28 | Mistral-7B-Instruct-v0.3mistralai | — | 555.7K | +555.7K | 3,730 | 7.2B |
| 29 | Bio_ClinicalBERTemilyalsentzer | Fill Mask | 553.8K | +553.8K | 440 | — |
| 30 | Huihui-Qwen3.8-27B-abliterated-GGUFhuihui-ai | Image Text to Text | 550.2K | +550.2K | 1,218 | — |
| 31 | prot_t5_xl_half_uniref50-encRostlab | — | 549.9K | +549.9K | 19 | — |
| 32 | chronos-bolt-tinyautogluon | Time Series Forecasting | 546.9K | +546.9K | 13 | 8.7M |
| 33 | Qwen3.5-0.8BQwen | Image Text to Text | 545.7K | +545.7K | 751 | 873M |
| 34 | gemma-4-12b-it-GGUFunsloth | Image Text to Text | 544.1K | +544.1K | 882 | — |
| 35 | Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen | Text to Speech | 543K | +543K | 2,035 | 1.9B |
| 36 | Qwen3.8-27B-Uncensored-GGUFJonathanColetti | Text Generation | 542.4K | +542.4K | 1,492 | — |
| 37 | tf_efficientnetv2_s.in21k_ft_in1ktimm | Image Classification | 541.3K | +541.3K | 5 | 21.6M |
| 38 | Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUFDavidAU | Image Text to Text | 538.6K | +538.6K | 978 | — |
| 39 | TRELLIS.2-4Bmicrosoft | Image To 3d | 535.5K | +535.5K | 1,298 | — |
| 40 | Qwen3-Embedding-4BQwen | Embeddings | 535.4K | +535.4K | 333 | 4B |
| 41 | paraphrase-mpnet-base-v2sentence-transformers | Sentence Similarity | 528.9K | +528.9K | 51 | 109M |
| 42 | Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFHauhauCS | Image Text to Text | 522.3K | +522.3K | 1,691 | — |
| 43 | Qwen3-VL-4B-InstructQwen | Image Text to Text | 516.5K | +516.5K | 488 | 4.4B |
| 44 | deepseek-v4.1-flash-ggufantirez | — | 513.8K | +513.8K | 57 | — |
| 45 | spkrec-ecapa-voxcelebspeechbrain | — | 510.9K | +510.9K | 349 | — |
| 46 | chronos-bolt-baseautogluon | Time Series Forecasting | 504.5K | +504.5K | 34 | 205M |
| 47 | vitpose-plus-baseusyd-community | Keypoint Detection | 503.7K | +503.7K | 36 | 125M |
| 48 | gte-reranker-modernbert-baseAlibaba-NLP | Text Ranking | 501.4K | +501.4K | 98 | 150M |
| 49 | moondream2vikhyatk | Image Text to Text | 501.2K | +501.2K | 1,437 | 1.9B |
| 50 | jina-embeddings-v3jinaai | Embeddings | 500.9K | +500.9K | 1,157 | 572M |