| 1 | gemma-3-27b-itgoogle | Image Text to Text | 2,013 | — | 2,013 | 27.4B |
| 2 | Sulphur-2-baseSulphurAI | Text to Video | 2,010 | — | 2,010 | — |
| 3 | GLM-OCRzai-org | Image Text to Text | 1,997 | — | 1,997 | 1.3B |
| 4 | Qwen3.5-9B-Uncensored-HauhauCS-AggressiveHauhauCS | — | 1,936 | — | 1,936 | — |
| 5 | Qwen2.5-Omni-7BQwen | Any to Any | 1,925 | — | 1,925 | 10.7B |
| 6 | Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen | Text to Speech | 1,902 | — | 1,902 | 1.9B |
| 7 | IP-Adapter-FaceIDh94 | Text to Image | 1,876 | — | 1,876 | — |
| 8 | embeddinggemma-300mgoogle | Sentence Similarity | 1,854 | — | 1,854 | 303M |
| 9 | Mistral-7B-Instruct-v0.1mistralai | Text Generation | 1,850 | — | 1,850 | 7.2B |
| 10 | Qwen3.5-9BQwen | Image Text to Text | 1,849 | — | 1,849 | 9.7B |
| 11 | zephyr-7b-betaHuggingFaceH4 | Text Generation | 1,849 | — | 1,849 | 7.2B |
| 12 | Florence-2-largemicrosoft | Image Text to Text | 1,847 | — | 1,847 | 777M |
| 13 | GLM-5.1zai-org | Text Generation | 1,840 | — | 1,840 | 754B |
| 14 | LTX-2.3Lightricks | Image To Video | 1,831 | — | 1,831 | — |
| 15 | Mixtral-8x7B-v0.1mistralai | — | 1,825 | — | 1,825 | 46.7B |
| 16 | GLM-4.7-Flashzai-org | Text Generation | 1,820 | — | 1,820 | 31.2B |
| 17 | c4ai-command-r-plusCohereLabs | Text Generation | 1,815 | — | 1,815 | 104B |
| 18 | controlnet-union-sdxl-1.0xinsir | Text to Image | 1,813 | — | 1,813 | 1.3B |
| 19 | Hunyuan3D-2tencent | Image To 3d | 1,803 | — | 1,803 | — |
| 20 | whisper-large-v2openai | Speech Recognition | 1,803 | — | 1,803 | 1.5B |
| 21 | LTX-2Lightricks | Image To Video | 1,776 | — | 1,776 | 18.9B |
| 22 | Muse-Glimmer-30Bmeta-models | Image Text to Text | 1,763 | — | 1,763 | 29.8B |
| 23 | chatterboxResembleAI | Text to Speech | 1,758 | — | 1,758 | — |
| 24 | QwQ-32B-PreviewQwen | Text Generation | 1,743 | — | 1,743 | 32.8B |
| 25 | Inklingthinkingmachines | Image Text to Text | 1,741 | — | 1,741 | 952B |
| 26 | TinyLlama-1.1B-Chat-v1.0TinyLlama | Text Generation | 1,740 | — | 1,740 | 1.1B |
| 27 | dreamlike-photoreal-2.0dreamlike-art | Text to Image | 1,732 | — | 1,732 | 860M |
| 28 | privacy-filteropenai | Token Classification | 1,730 | — | 1,730 | 1.4B |
| 29 | OmniParsermicrosoft | Image Text to Text | 1,714 | — | 1,714 | — |
| 30 | Kimi-K2-Thinkingmoonshotai | Text Generation | 1,712 | — | 1,712 | 1.1T |
| 31 | Reflection-Llama-3.1-70Bmattshumer | Text Generation | 1,710 | — | 1,710 | 70.6B |
| 32 | Gemma-4-31B-JANG_4M-CRACKdealignai | Image Text to Text | 1,707 | — | 1,707 | 6.4B |
| 33 | DeepSeek-V3-Basedeepseek-ai | — | 1,704 | — | 1,704 | 685B |
| 34 | Phi-3-mini-128k-instructmicrosoft | Text Generation | 1,703 | — | 1,703 | 3.8B |
| 35 | Mistral-Nemo-Instruct-2407mistralai | — | 1,694 | — | 1,694 | 12.2B |
| 36 | Qwen2.5-VL-7B-InstructQwen | Image Text to Text | 1,684 | — | 1,684 | 8.3B |
| 37 | ChatTTS2Noise | Text to Audio | 1,667 | — | 1,667 | — |
| 38 | WAN2.2-14B-Rapid-AllInOnePhr00t | Image To Video | 1,653 | — | 1,653 | — |
| 39 | PaddleOCR-VLPaddlePaddle | Image Text to Text | 1,647 | — | 1,647 | 959M |
| 40 | LTX-2.5Lightricks | Image To Video | 1,645 | — | 1,645 | — |
| 41 | Llama-3.2-11B-Vision-Instructmeta-llama | Image Text to Text | 1,634 | — | 1,634 | 10.7B |
| 42 | SmolDocling-256M-previewdocling-project | Image Text to Text | 1,618 | — | 1,618 | 256M |
| 43 | Phi-4-multimodal-instructmicrosoft | Speech Recognition | 1,613 | — | 1,613 | 5.6B |
| 44 | Qwen3-Coder-NextQwen | Text Generation | 1,613 | — | 1,613 | 79.7B |
| 45 | bart-large-cnnfacebook | Summarization | 1,609 | — | 1,609 | 406M |
| 46 | DeepSeek-R1-Distill-Qwen-32Bdeepseek-ai | Text Generation | 1,598 | — | 1,598 | 32.8B |
| 47 | bart-large-mnlifacebook | Zero-Shot Classification | 1,597 | — | 1,597 | 407M |
| 48 | Nanonets-OCR-snanonets | Image Text to Text | 1,592 | — | 1,592 | 3.8B |
| 49 | Kimi-K2.6moonshotai | Image Text to Text | 1,592 | — | 1,592 | 1T |
| 50 | Counterfeit-V2.5gsdf | Text to Image | 1,586 | — | 1,586 | 860M |