| 1 | donut-basenaver-clova-ix | Image to Text | 57.9K | — | 254 | — |
| 2 | chinese-roberta-wwm-exthfl | Fill Mask | 57.8K | — | 424 | — |
| 3 | ner-english-largeflair | Token Classification | 57.7K | — | 53 | — |
| 4 | resnet34d.ra2_in1ktimm | Image Classification | 57.7K | — | 0 | 21.8M |
| 5 | gliner_multi_pii-v1urchade | Token Classification | 57.6K | — | 173 | — |
| 6 | gemma-4-31B-it-uncensored-heretic-GGUFllmfan46 | Image Text to Text | 57.6K | — | 179 | — |
| 7 | Qwen2.5-72B-Instruct-GPTQ-Int4Qwen | Text Generation | 57.6K | — | 44 | 73B |
| 8 | distilbart-mnli-12-1valhalla | Zero-Shot Classification | 57.6K | — | 56 | — |
| 9 | st-codesearch-distilroberta-baseflax-sentence-embeddings | Sentence Similarity | 57.6K | — | 33 | — |
| 10 | Qwen3.5-9Bhamishivi | Image Text to Text | 57.4K | — | 0 | 9.7B |
| 11 | opus-mt-eu-esHelsinki-NLP | Translation | 57.4K | — | 1 | — |
| 12 | MiniLM-L12-H384-uncasedmicrosoft | Text Classification | 57.4K | — | 111 | — |
| 13 | step3stepfun-ai | Image Text to Text | 57.4K | — | 166 | 321B |
| 14 | HyperCLOVAX-SEED-Vision-Instruct-3Bnaver-hyperclovax | Text Generation | 57.4K | — | 221 | 3.7B |
| 15 | bert_uncased_L-4_H-512_A-8google | — | 57.4K | — | 5 | — |
| 16 | bloom-1b7bigscience | Text Generation | 57.3K | — | 123 | 1.7B |
| 17 | glm-4v-9bzai-org | — | 57.3K | — | 268 | 13.9B |
| 18 | banglabertcsebuetnlp | — | 57.2K | — | 44 | — |
| 19 | whisper-large-v3-turbo-armenianChillarmo | Speech Recognition | 57.1K | — | 3 | 809M |
| 20 | hassaku-xl-illustrious-v31-sdxlJohn6666 | Text to Image | 57K | — | 2 | 2.6B |
| 21 | google_gemma-4-31B-it-GGUFbartowski | Image Text to Text | 57K | — | 86 | — |
| 22 | command-a-plus-05-2026-bf16CohereLabs | Image Text to Text | 57K | — | 141 | 219B |
| 23 | wav2vec2-large-robust-L2-english-phoneme-recognitionslplab | Speech Recognition | 57K | — | 5 | 316M |
| 24 | gliner_multi-v2.1urchade | Token Classification | 57K | — | 170 | 289M |
| 25 | progen2-smallhugohrban | Text Generation | 56.9K | — | 2 | 151M |
| 26 | prot_bertRostlab | Fill Mask | 56.9K | — | 135 | — |
| 27 | phi-1_5microsoft | Text Generation | 56.8K | — | 1,361 | 1.4B |
| 28 | Qwen3-VL-30B-A3B-Instruct-AWQ-4bitcyankiwi | Image Text to Text | 56.8K | — | 10 | 5.8B |
| 29 | sentiment-roberta-large-englishsiebert | Text Classification | 56.8K | — | 158 | — |
| 30 | smol-tools-4b-32kenfuse | Text Generation | 56.8K | — | 1 | 5.2B |
| 31 | PP-OCRv5_mobile_detPaddlePaddle | Image to Text | 56.8K | — | 30 | — |
| 32 | PP-OCRv6_medium_detPaddlePaddle | Image to Text | 56.8K | — | 29 | — |
| 33 | Qwen3.6-27B-AWQ-6BitQuantTrio | Image Text to Text | 56.7K | — | 17 | 27.8B |
| 34 | hunyuan3D_2.1_repackagedComfy-Org | — | 56.7K | — | 21 | — |
| 35 | Qwen3.6-27B-DFlash-GGUF-llama.cppAlittlehammmer | Text Generation | 56.7K | — | 19 | — |
| 36 | LTX2.3-ICEdit-Insightjoyfox | Video To Video | 56.7K | — | 169 | — |
| 37 | chronos-t5-miniamazon | Time Series Forecasting | 56.6K | — | 20 | 20.5M |
| 38 | Qwen3-0.6B-unsloth-bnb-4bitunsloth | Text Generation | 56.5K | — | 27 | 609M |
| 39 | llava-v1.6-vicuna-7bliuhaotian | Image Text to Text | 56.5K | — | 144 | 7.1B |
| 40 | granite-embedding-30m-englishibm-granite | Sentence Similarity | 56.5K | — | 30 | 30.3M |
| 41 | rtdetr_r18vdPekingU | Object Detection | 56.5K | — | 6 | 20.2M |
| 42 | gemma-4-26B-A4B-it-GGUFggml-org | Image Text to Text | 56.4K | — | 80 | — |
| 43 | chronos-t5-tinyautogluon | Time Series Forecasting | 56.4K | — | 11 | 8.4M |
| 44 | BioBERT-mnli-snli-scinli-scitail-mednli-stsbpritamdeka | Sentence Similarity | 56.4K | — | 58 | — |
| 45 | mt5-basegoogle | — | 56.4K | — | 264 | — |
| 46 | Qwen3.8-27B-W4A16-AutoRounddbirks | Image Text to Text | 56.3K | — | 14 | 6.3B |
| 47 | bart-large-mnli-yahoo-answersjoeddav | Zero-Shot Classification | 56.3K | — | 13 | 407M |
| 48 | FLUX.2-klein-9b-fp8black-forest-labs | Image To Image | 56.3K | — | 379 | — |
| 49 | Nanbeige4.2-3BNanbeige | Text Generation | 56.3K | — | 714 | 4.2B |
| 50 | granite-4.0-1b-speechibm-granite | Speech Recognition | 56.2K | — | 251 | 2.3B |