| 1 | Nanbeige4.3-33B-NVFP4webbrain-one | Text Generation | 18 | — | 19 | 19.7B |
| 2 | ncm-checkpointshazyresearch | Text Generation | 18 | — | 51 | — |
| 3 | MOSS-Image-color-depth-controldarask0 | Text to Image | 18 | — | 37 | — |
| 4 | Qwen3.8-27B-Uncensored-MLXorcarouter | Image Text to Text | 18 | ▲13.7%(up) | 1,599 | 27.4B |
| 5 | Tiel-Coder-35B-A3B-GGUFpeculiar-ragdoll | Image Text to Text | 18 | ▲21.3%(up) | 409 | — |
| 6 | Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth | Text Generation | 18 | ▲11.9%(up) | 1,183 | — |
| 7 | Nanbeige_Nanbeige4.3-33B-GGUFbartowski | Text Generation | 18 | — | 19 | — |
| 8 | Phonon-2.5-EnglishFermionResearch | Speech Recognition | 18 | — | 18 | — |
| 9 | Nemotron-3.5-Embed-8B-BF16nvidia | Visual Document Retrieval | 18 | — | 31 | 8.4B |
| 10 | Qwen3.5-4B-GGUFunsloth | Image Text to Text | 18 | ▲4.2%(up) | 522 | — |
| 11 | Nemotron-3.5-Embed-1B-NVFP4nvidia | Visual Document Retrieval | 18 | — | 22 | 1.6B |
| 12 | Wan2.2-TI2V-5BWan-AI | Text to Video | 18 | ▲4.6%(up) | 889 | — |
| 13 | stable-audio-3-small-sfxstabilityai | Text to Audio | 18 | ▲11.5%(up) | 300 | 568M |
| 14 | timesfm-3.0-pytorchgoogle | Time Series Forecasting | 18 | ▲33.6%(up) | 995 | 331M |
| 15 | MiniMax-Music3MiniMaxAI | Text to Audio | 18 | ▲6.8%(up) | 1,484 | 2.4B |
| 16 | MiniCPM5-2Bopenbmb | Text Generation | 18 | ▲122.7%(up) | 1,824 | 2.5B |
| 17 | Qwen2.5-Coder-7B-Instruct-GGUFQwen | Text Generation | 18 | ▲5.6%(up) | 598 | — |
| 18 | dinov3-vitb16-pretrain-lvd1689mfacebook | Image Feature Extraction | 18 | ▲1.6%(up) | 511 | 85.7M |
| 19 | GPT-X3-150MAxiomicLabs | Text Generation | 18 | — | 93 | 149M |
| 20 | Qwen3-8B-GGUFQwen | Text Generation | 18 | ▲7.7%(up) | 359 | — |
| 21 | DeepSeek-V4.1-Flash-1017-EXL3-EAQ-v1-2.9-bpwMia-AiLab | Image Text to Text | 18 | — | 34 | 105B |
| 22 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16nvidia | Image Text to Text | 18 | — | 103 | 124B |
| 23 | nemotron-3.5-asr-streaming-0.6bnvidia | Speech Recognition | 17 | ▲9.5%(up) | 1,240 | 638M |
| 24 | nemotron-labs-unified-asr-0.6bnvidia | Speech Recognition | 17 | — | 17 | — |
| 25 | GLM-5.3-Flash-FP4-Localnvidia | Image Text to Text | 17 | — | 126 | 175B |
| 26 | Qwen3.8-40B-UltimateDavidAU | Image Text to Text | 17 | — | 17 | 40B |
| 27 | gemma-4-E4B-it-ultra-uncensored-heretic-GGUFllmfan46 | Any to Any | 17 | ▲4.2%(up) | 274 | — |
| 28 | embeddinggemma-2-GGUFunsloth | Embeddings | 17 | — | 354 | — |
| 29 | z_image_turboComfy-Org | — | 17 | ▲5.3%(up) | 990 | — |
| 30 | GLiNER2.5-Decidefastino | Text Classification | 17 | — | 438 | 486M |
| 31 | OlmoEarth-v1_3-Baseallenai | Image Feature Extraction | 17 | — | 17 | — |
| 32 | DeepSeek-V4.1-Flash-1017-BLACKFOLD-EXL3-2.9bpw-TP2BlackwellBoy | Text Generation | 17 | — | 26 | — |
| 33 | audio.cpp-ggufaudio-cpp | Text to Speech | 17 | ▲44.1%(up) | 279 | — |
| 34 | Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-GGUFLuffyTheFox | Image Text to Text | 17 | 0% | 611 | — |
| 35 | Z-Image-TurboTongyi-MAI | Text to Image | 17 | ▲1.5%(up) | 5,522 | 6.2B |
| 36 | Mellum2.1-12B-A2.5B-Thinking-GGUFJetBrains | Text Generation | 17 | — | 154 | — |
| 37 | Flora-Captionernvidia | Image Text to Text | 17 | — | 36 | 27.4B |
| 38 | Qwen3.8-27B-Uncensoredorcarouter | Image Text to Text | 17 | ▲5.8%(up) | 494 | 27.8B |
| 39 | Ornith-1.5-35B-A3Bornith-ai | Text Generation | 17 | ▲17.8%(up) | 761 | 36B |
| 40 | Llama-3.2-1B-Instructmeta-llama | Text Generation | 17 | ▲2.1%(up) | 1,911 | 1.2B |
| 41 | maya1maya-research | Text to Speech | 17 | ▲0.3%(up) | 937 | 3.3B |
| 42 | Ming-3.0-audio-tinyinclusionAI | Text to Speech | 17 | — | 51 | 8.9B |
| 43 | Qwen3.8-31B-Looping-TransformerDavidAU | Image Text to Text | 17 | — | 17 | 30.8B |
| 44 | gemma-4-26B-A4B-itgoogle | Image Text to Text | 16 | ▲5.0%(up) | 1,712 | 25.8B |
| 45 | sam-3d-objectsfacebook | — | 16 | ▲2.7%(up) | 607 | — |
| 46 | flint-40B-A2.5B-Q4_K_M-GGUFAbiray | — | 16 | — | 16 | — |
| 47 | Ornith1.0-9B-3MPER0RR-abliterated-GGUFmradermacher | — | 16 | — | 17 | — |
| 48 | FLUX-3-Image-Klein-GGUFAtomicChat | Text to Image | 16 | — | 16 | — |
| 49 | Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRotethanfel | Image Text to Text | 16 | — | 741 | — |
| 50 | RMBG-2.0briaai | Image Segmentation | 16 | ▲1.0%(up) | 1,584 | 221M |