| 1 | Qwen3-TTS-12Hz-1.7B-BaseQwen | — | 1M | +1M | 540 | 1.9B |
| 2 | bge-base-en-v1.5-course-recommender-v5datasocietyco | Sentence Similarity | 970.3K | +970.3K | 5 | 109M |
| 3 | Qwen3-32BQwen | Text Generation | 965.4K | +965.4K | 754 | 32.8B |
| 4 | gpt-oss-120bopenai | Text Generation | 957.1K | +957.1K | 5,360 | 117B |
| 5 | MiniMax-H3MiniMaxAI | Image Text To Video | 943.1K | +943.1K | 5,917 | 33.1B |
| 6 | siglip2-base-patch16-256google | Zero-Shot Image Classification | 921.7K | +921.7K | 17 | 375M |
| 7 | DeepSeek-V3.2deepseek-ai | Text Generation | 915.2K | +915.2K | 1,505 | 685B |
| 8 | DeepSeek-V4-Flash-0731deepseek-ai | Text Generation | 904.3K | +904.3K | 4,017 | 304B |
| 9 | faster-whisper-smallSystran | Speech Recognition | 886.2K | +886.2K | 58 | — |
| 10 | all-MiniLM-L6-v2Xenova | Embeddings | 882.5K | +882.5K | 153 | — |
| 11 | all-MiniLM-L12-v2sentence-transformers | Sentence Similarity | 876.7K | +876.7K | 330 | 33.4M |
| 12 | whisper-large-v3openai | Speech Recognition | 876.1K | +876.1K | 6,568 | 1.5B |
| 13 | inclusively-reformulation-it5E-MIMIC | — | 876K | +876K | 2 | 783M |
| 14 | Qwen3-14BQwen | Text Generation | 858K | +858K | 489 | 14.8B |
| 15 | wav2vec2-large-xlsr-53-polishjonatasgrosman | Speech Recognition | 855.4K | +855.4K | 14 | — |
| 16 | bert-base-casedgoogle-bert | Fill Mask | 851.8K | +851.8K | 380 | 109M |
| 17 | pythia-160mEleutherAI | Text Generation | 845.3K | +845.3K | 46 | 213M |
| 18 | Qwen3-1.7BQwen | Text Generation | 841.6K | +841.6K | 565 | 2B |
| 19 | Prompt-Guard-86Mmeta-llama | Text Classification | 839.3K | +839.3K | 420 | 279M |
| 20 | CLIP-ViT-B-32-laion2B-s34B-b79Klaion | Zero-Shot Image Classification | 831.3K | +831.3K | 145 | 151M |
| 21 | CLIP-ViT-L-14-laion2B-s32B-b82Klaion | Zero-Shot Image Classification | 817.3K | +817.3K | 67 | 428M |
| 22 | bert-base-chinesegoogle-bert | Fill Mask | 794.8K | +794.8K | 1,472 | 103M |
| 23 | Qwen3.6-35B-A3BQwen | Image Text to Text | 794.5K | +794.5K | 2,928 | 36B |
| 24 | nomic-embed-text-v1nomic-ai | Sentence Similarity | 788.2K | +788.2K | 584 | 137M |
| 25 | wav2vec2-indonesian-javanese-sundaneseindonesian-nlp | Speech Recognition | 778.3K | +778.3K | 15 | — |
| 26 | Ornith-1.5-35B-A3B-GGUFornith-ai | Text Generation | 772.3K | +772.3K | 484 | — |
| 27 | indonesian-roberta-base-posp-taggerw11wo | Token Classification | 770.4K | +770.4K | 10 | 124M |
| 28 | OTel-2.0-LLM-31B-ITfarbodtavakkoli | Text Generation | 768.1K | +768.1K | 22 | 31.3B |
| 29 | Qwen3.8-27B-NVFP4unsloth | — | 767.7K | +767.7K | 494 | 19.9B |
| 30 | wav2vec2-large-xlsr-53-arabicjonatasgrosman | Speech Recognition | 763K | +763K | 55 | — |
| 31 | twitter-roberta-base-sentiment-latestcardiffnlp | Text Classification | 760.8K | +760.8K | 834 | — |
| 32 | Florence-2-basemicrosoft | Image Text to Text | 758.6K | +758.6K | 402 | 232M |
| 33 | Wan_2.1_ComfyUI_repackagedComfy-Org | — | 758.1K | +758.1K | 993 | — |
| 34 | bert-base-multilingual-uncasedgoogle-bert | Fill Mask | 744.7K | +744.7K | 161 | 168M |
| 35 | dinov2-basefacebook | Image Feature Extraction | 736.5K | +736.5K | 202 | 86.6M |
| 36 | JiRackUltra_14bCMSManhattan | Text Generation | 736.1K | +736.1K | 2 | 14.8B |
| 37 | Qwen2.5-7B-Instruct-AWQQwen | Text Generation | 734.6K | +734.6K | 53 | 7.6B |
| 38 | distilbert-base-uncased-finetuned-sst-2-englishdistilbert | Text Classification | 734.2K | +734.2K | 965 | 67M |
| 39 | Qwen-72BQwen | Text Generation | 731.2K | +731.2K | 364 | 72.3B |
| 40 | stable-diffusion-v1-5stable-diffusion-v1-5 | Text to Image | 722.9K | +722.9K | 1,302 | 860M |
| 41 | esm2_t33_650M_UR50Dfacebook | Fill Mask | 711.9K | +711.9K | 93 | 652M |
| 42 | Qwen3-Embedding-8BQwen | Embeddings | 709K | +709K | 820 | 7.6B |
| 43 | bge-reranker-largeBAAI | Embeddings | 705K | +705K | 472 | 560M |
| 44 | deberta-v3-basemicrosoft | Fill Mask | 699.5K | +699.5K | 447 | — |
| 45 | whisper-smallopenai | Speech Recognition | 696.3K | +696.3K | 611 | 242M |
| 46 | all-distilroberta-v1sentence-transformers | Sentence Similarity | 693.4K | +693.4K | 44 | 82.1M |
| 47 | mms-300m-1130-forced-alignerMahmoudAshraf | Speech Recognition | 692.7K | +692.7K | 105 | 315M |
| 48 | finbert-toneyiyanghkust | Text Classification | 682.2K | +682.2K | 224 | — |
| 49 | wav2vec2-large-xlsr-53-dutchjonatasgrosman | Speech Recognition | 661.8K | +661.8K | 18 | — |
| 50 | Qwen3-14B-AWQQwen | Text Generation | 661.7K | +661.7K | 75 | 14.8B |