| 1 | Audio2Face-3D-v2.3.1-Jamesnvidia | — | 2 | — | 11 | — |
| 2 | rad-dino-maira-2microsoft | Image Feature Extraction | 2 | ▲1.7%(up) | 30 | 86.6M |
| 3 | JoyAI-Image-Edit-Plus-Diffusersjdopensource | Image To Image | 2 | 0% | 27 | 16.3B |
| 4 | bigbird-roberta-basegoogle | — | 2 | ▲0.8%(up) | 68 | — |
| 5 | Kromoss-GGUFmolbal | Text to Image | 2 | — | 2 | — |
| 6 | Mixtral-8x7B-Instruct-v0.1mistralai | — | 2 | ▲0.2%(up) | 4,776 | 46.7B |
| 7 | Qwen1.5-110B-Chat-AWQQwen | Text Generation | 2 | — | 14 | 111B |
| 8 | Qwen3Guard-Gen-0.6BQwen | Text Generation | 2 | ▲0.7%(up) | 96 | 752M |
| 9 | LYRAMOONmuhammad-taqi512 | Text Generation | 2 | — | 2 | 7.6B |
| 10 | siglip-large-patch16-256google | Zero-Shot Image Classification | 2 | ▲0.1%(up) | 20 | 652M |
| 11 | WhereOPD-Qwen3.5-9B-GGUFprithivMLmods | Image Text to Text | 2 | — | 2 | — |
| 12 | Qwen3.8-27B-Uncensored-NVFP4piscesbody | Text Generation | 2 | — | 3 | 18.2B |
| 13 | vit-base-patch16-224-in21kgoogle | Image Feature Extraction | 2 | ▲0.2%(up) | 432 | 86.4M |
| 14 | Qwen-1_8B-Chat-Int4Qwen | Text Generation | 2 | — | 42 | 1.8B |
| 15 | DeepSeek-V4.1-Flash-EXL3-2.7bpwsudoingx | — | 2 | — | 9 | — |
| 16 | imagine-v9Interchained | Text Generation | 2 | — | 2 | 1.3B |
| 17 | beit-large-patch16-384microsoft | Image Classification | 2 | ▲0.3%(up) | 6 | — |
| 18 | Qwen3-1.7B-GGUFQwen | Text Generation | 2 | ▲6.4%(up) | 85 | — |
| 19 | Qwen3.8-Flash-Next-Abliterated-NVFP4windowsxp811203 | Image Text to Text | 2 | — | 6 | 117B |
| 20 | Qwen3.8-Flash-Next-JANG_6SJANGQ-AI | Image Text to Text | 2 | ▲9.8%(up) | 5 | 180B |
| 21 | Cydonia-24B-v4.3-GGUFTheDrummer | — | 2 | ▲9.1%(up) | 100 | — |
| 22 | DeepSeek-R1-Distill-Llama-8B-Abliterated-i1-GGUFmradermacher | — | 2 | ▲2.0%(up) | 9 | — |
| 23 | LongCat-Videomeituan-longcat | Text to Video | 2 | ▲2.7%(up) | 587 | — |
| 24 | HiDream-I1-FullHiDream-ai | Text to Image | 2 | ▲0.0%(up) | 1,010 | 17.1B |
| 25 | Hy4-preview-NVFP4-W4A16Oxmiq | Text Generation | 2 | — | 2 | 780B |
| 26 | VibeVoice-ASR-Streaming-1.5Bmicrosoft | Speech Recognition | 2 | ▲47.2%(up) | 64 | 2.8B |
| 27 | Qwen3-4B-MLX-8bitQwen | Text Generation | 2 | — | 8 | 4B |
| 28 | wavlm-base-plusmicrosoft | Embeddings | 2 | ▲0.3%(up) | 49 | — |
| 29 | Rex-Omni-AWQIDEA-Research | — | 2 | ▲1.1%(up) | 7 | 3.8B |
| 30 | Qwen3.5-35B-A3B-MTP-GGUFunsloth | Image Text to Text | 2 | ▲3.0%(up) | 23 | — |
| 31 | Fenrir-X-26B-A4BVortex5 | Image Text to Text | 2 | — | 16 | 25.8B |
| 32 | GLM-5.3-Flash-ewaste-edition-GGUFSixVolts | Text Generation | 2 | — | 4 | — |
| 33 | Qwen3.8-27B-abliteratedhotdogs | Image Text to Text | 2 | ▲9.3%(up) | 15 | 27.8B |
| 34 | siglip2-large-patch16-384google | Zero-Shot Image Classification | 2 | ▲1.6%(up) | 9 | 882M |
| 35 | vit-large-patch32-224-in21kgoogle | Image Feature Extraction | 2 | ▲1.9%(up) | 7 | — |
| 36 | mobilebert-uncasedgoogle | — | 2 | ▲0.1%(up) | 81 | — |
| 37 | SignOfFourpragmaticcs | Text Generation | 2 | 0% | 2 | 35.1B |
| 38 | Instinct-Python-Coder-Gemma4-12B-Qwen3.8-27Bprojectj | Text Generation | 2 | — | 7 | — |
| 39 | t5-11b-ssm-tqagoogle | — | 2 | — | 19 | — |
| 40 | jina-embeddings-v5-text-small-classificationjinaai | Text Classification | 2 | ▲1.9%(up) | 11 | 596M |
| 41 | Qwen-Image-Edit-GGUFQuantStack | Image To Image | 2 | ▲1.0%(up) | 304 | — |
| 42 | Qwen3.8-Flash-Next-GSQ-RCO-GGUFpfeifferj | Image Text to Text | 2 | ▲1,271.93%(up) | 53 | — |
| 43 | HunyuanImage-3.0-Instruct-Distiltencent | Image To Image | 2 | ▲3.6%(up) | 69 | 83B |
| 44 | Tokle-3Mtechdotus | Text Generation | 2 | — | 16 | 2.9M |
| 45 | chatterbox-flashResembleAI | Text to Speech | 2 | — | 30 | — |
| 46 | physical-plausibility-evaluatornvidia | — | 2 | — | 2 | — |
| 47 | Mistral-Small-Instruct-2409mistralai | — | 2 | ▲0.0%(up) | 406 | 22.2B |
| 48 | Qwen2-7B-InstructQwen | Text Generation | 2 | ▲0.4%(up) | 695 | 7.6B |
| 49 | microsoft-AesCode-8B-MLXprithivMLmods | Image Text to Text | 2 | — | 2 | 8.8B |
| 50 | Kolibri-1-NVFP4-W4A16audreyt | Text Generation | 2 | — | 5 | 40.3B |