| 1 | Qwen3.5-4BQwen | Image Text to Text | 7.7M | — | 841 | 4.7B |
| 2 | Llama-3.2-1B-Instructmeta-llama | Text Generation | 7.6M | — | 1,581 | 1.2B |
| 3 | Qwen2.5-3B-InstructQwen | Text Generation | 7.5M | — | 552 | 3.1B |
| 4 | multilingual-e5-largeintfloat | Embeddings | 7.5M | — | 1,242 | 560M |
| 5 | gpt-oss-20bopenai | Text Generation | 7.2M | — | 4,946 | 20.9B |
| 6 | OTel-2.0-LLM-31B-ITfarbodtavakkoli | Text Generation | 7.1M | — | 14 | 32.1B |
| 7 | distilbert-base-uncaseddistilbert | Fill Mask | 7.1M | — | 934 | 67M |
| 8 | Qwen3-Embedding-0.6BQwen | Embeddings | 7M | — | 1,165 | 596M |
| 9 | Qwen2.5-0.5B-InstructQwen | Text Generation | 6.8M | — | 598 | 494M |
| 10 | Qwen3.8-27B-GGUFunsloth | — | 6.7M | — | 2,741 | — |
| 11 | wespeaker-voxceleb-resnet34-LMpyannote | — | 6.6M | — | 161 | — |
| 12 | Llama-3.1-8B-Instructmeta-llama | Text Generation | 6.5M | — | 6,654 | 8B |
| 13 | Qwen3.6-27BQwen | Image Text to Text | 6.3M | — | 2,279 | 27.8B |
| 14 | clip-vit-large-patch14openai | Zero-Shot Image Classification | 6.3M | — | 2,072 | 428M |
| 15 | z_image_turboComfy-Org | — | 6.3M | — | 832 | — |
| 16 | multilingual-e5-baseintfloat | Sentence Similarity | 6.2M | — | 380 | 278M |
| 17 | segmentation-3.0pyannote | Voice Activity Detection | 6.1M | — | 1,542 | — |
| 18 | Qwen2.5-VL-3B-InstructQwen | Image Text to Text | 6M | — | 688 | 3.8B |
| 19 | Qwen3-VL-8B-InstructQwen | Image Text to Text | 5.5M | — | 1,059 | 8.8B |
| 20 | chronos-2autogluon | Time Series Forecasting | 5.4M | — | 48 | 119M |
| 21 | Qwen3.6-35B-A3BQwen | Image Text to Text | 5.4M | — | 2,730 | 36B |
| 22 | ModernBERT-baseanswerdotai | Fill Mask | 5.4M | — | 1,087 | 150M |
| 23 | speaker-diarization-community-1pyannote | Speech Recognition | 5.3M | — | 1,124 | — |
| 24 | gemma-4-E4B-itgoogle | Any to Any | 5.3M | — | 1,499 | 8B |
| 25 | xlm-roberta-largeFacebookAI | Fill Mask | 5.2M | — | 526 | 561M |
| 26 | DeepSeek-R1deepseek-ai | Text Generation | 5.2M | — | 13.6K | 685B |
| 27 | chronos-bolt-smallamazon | Time Series Forecasting | 5.2M | — | 20 | 47.7M |
| 28 | wav2vec2-large-xlsr-53-portuguesejonatasgrosman | Speech Recognition | 5M | — | 55 | — |
| 29 | Qwen3-4BQwen | Text Generation | 5M | — | 684 | 4B |
| 30 | granite-embedding-small-english-r2ibm-granite | Embeddings | 5M | — | 76 | 47.7M |
| 31 | Wan_2.2_ComfyUI_RepackagedComfy-Org | Image To Video | 5M | — | 845 | — |
| 32 | gpt-oss-120bopenai | Text Generation | 4.9M | — | 5,120 | 117B |
| 33 | gemma-3-1b-itgoogle | Text Generation | 4.9M | — | 1,104 | 1000M |
| 34 | dinov2-smallfacebook | Image Feature Extraction | 4.9M | — | 71 | 22.1M |
| 35 | mdeberta-v3-basemicrosoft | Fill Mask | 4.8M | — | 232 | — |
| 36 | Qwen3-1.7BQwen | Text Generation | 4.8M | — | 523 | 2B |
| 37 | finbertProsusAI | Text Classification | 4.8M | — | 1,222 | — |
| 38 | vit-base-patch16-224google | Image Classification | 4.8M | — | 992 | 86.6M |
| 39 | Ornith-1.0-9B-GGUFornith-ai | Text Generation | 4.7M | — | 657 | — |
| 40 | bge-small-zh-v1.5BAAI | Embeddings | 4.7M | — | 138 | 24M |
| 41 | dolphin-2.9.1-yi-1.5-34bdphn | Text Generation | 4.6M | — | 65 | 34.4B |
| 42 | Qwen3-ASR-1.7BQwen | Speech Recognition | 4.6M | — | 1,035 | 2.3B |
| 43 | whisper-large-v3openai | Speech Recognition | 4.6M | — | 6,176 | 1.5B |
| 44 | Prompt-Guard-86Mmeta-llama | Text Classification | 4.5M | — | 393 | 279M |
| 45 | segmentationpyannote | Voice Activity Detection | 4.5M | — | 692 | — |
| 46 | voice-activity-detectionpyannote | Speech Recognition | 4.5M | — | 241 | — |
| 47 | nomic-embed-text-v1nomic-ai | Sentence Similarity | 4.4M | — | 580 | 137M |
| 48 | Qwen2.5-7B-Instruct-AWQQwen | Text Generation | 4.3M | — | 50 | 7.6B |
| 49 | bert-base-multilingual-uncasedgoogle-bert | Fill Mask | 4.2M | — | 158 | 168M |
| 50 | bge-base-en-v1.5-course-recommender-v5datasocietyco | Sentence Similarity | 4.2M | — | 3 | 109M |