| 1 | NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bitDuckets | Image Text to Text | 2 | — | 2 | 74.9B |
| 2 | Audio-Flamingo-GGUFaudio-cpp | Speech Recognition | 2 | — | 6 | — |
| 3 | Param2-17B-A2.4B-Thinkingbharatgenai | Text Generation | 2 | ▲0.9%(up) | 84 | 17.2B |
| 4 | Qwen-35B-A3B-SignOfFour-Coder-GGUFpragmaticcs | Text Generation | 2 | ▲5.0%(up) | 8 | — |
| 5 | SAE-Res-Qwen3.5-35B-A3B-Base-W32K-L0_50Qwen | — | 2 | — | 12 | — |
| 6 | t5-11b-ssm-wqgoogle | — | 2 | — | 3 | — |
| 7 | mms-tts-uig-script_cyrillicfacebook | Text to Speech | 2 | — | 2 | 36.3M |
| 8 | gemma-3-270mgoogle | Text Generation | 2 | ▲0.1%(up) | 1,125 | 268M |
| 9 | mms-tts-sahfacebook | Text to Speech | 2 | — | 2 | 36.3M |
| 10 | mms-tts-kxmfacebook | Text to Speech | 2 | — | 3 | 36.3M |
| 11 | Qwen3-VL-8B-Instruct-GGUFunsloth | Image Text to Text | 2 | ▲2.6%(up) | 99 | — |
| 12 | moonshotai_Kimi-Linear-48B-A3B-Instruct-GGUFbartowski | Text Generation | 2 | ▲10.9%(up) | 30 | — |
| 13 | sam2.1-hiera-tinyfacebook | Mask Generation | 2 | ▲3.7%(up) | 30 | 39M |
| 14 | ARDY-Core-RP-20FPS-Horizon40nvidia | — | 2 | ▲6.0%(up) | 50 | — |
| 15 | Phoenix-X-26B-A4B-Heretic-GGUFmradermacher | — | 2 | 0% | 2 | — |
| 16 | Qwen3-VL-2B-Instruct-GGUFunsloth | Image Text to Text | 2 | ▲1.1%(up) | 47 | — |
| 17 | Qwen3.6-28B-REAP20-A3B-GGUFbarozp | Text Generation | 2 | ▲3.0%(up) | 86 | — |
| 18 | t5-v1_1-xxl-encoder-ggufcity96 | — | 2 | ▲1.1%(up) | 547 | — |
| 19 | Waifu-Inpaint-XLShinoharaHare | Image To Image | 2 | ▲2.0%(up) | 57 | 2.6B |
| 20 | muskxiangjx | Image to Text | 2 | — | 92 | 675M |
| 21 | LYRAMOONmuhammad-taqi512 | Text Generation | 2 | — | 2 | 7.6B |
| 22 | Swift-1.5-Qwen3.8-27b-ONNX-BF16ukisai | Image Text to Text | 2 | — | 2 | — |
| 23 | WhereOPD-Qwen3.5-9B-GGUFprithivMLmods | Image Text to Text | 2 | — | 2 | — |
| 24 | Cyber-Tiel-Coder-35B-A3B-MLX-oQ4epeculiar-ragdoll | Image Text to Text | 2 | — | 5 | 35.1B |
| 25 | Qwen3-1.7B-Q4_K_M-GGUFrippertnt | Text Generation | 2 | ▲26.2%(up) | 4 | — |
| 26 | Hy-Memory-30B-A3B-GGUFvinnipukh | Text Generation | 2 | — | 2 | — |
| 27 | Ornith-1.5-35B-A3B-GSQ-RCO-GGUFpfeifferj | Text Generation | 2 | — | 22 | — |
| 28 | ThinkingCap-Qwen3.8-27B-FP8bottlecapai | Image Text to Text | 2 | — | 17 | 27.8B |
| 29 | Qwen-Image-Layered_ComfyUIComfy-Org | — | 2 | ▲3.5%(up) | 69 | — |
| 30 | DeepSeek-V4.1-Flash-1017-MLX-mixed-4_8bitpipenetwork | Text Generation | 2 | — | 2 | 379B |
| 31 | imagine-v9Interchained | Text Generation | 2 | — | 2 | 1.3B |
| 32 | Ornith-1.5-9B-DFlashornith-ai | — | 2 | — | 25 | 1.3B |
| 33 | Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF-3060-benchgroxaxo | Text Generation | 2 | — | 3 | — |
| 34 | Winery-Qwen3.5-9B-Fable-Reserve-GGUFWineryLabs | Text Generation | 2 | — | 3 | — |
| 35 | SenseVoiceSmallFunAudioLLM | Speech Recognition | 2 | ▲3.0%(up) | 499 | — |
| 36 | dinov2-smallfacebook | Image Feature Extraction | 2 | ▲1.1%(up) | 84 | 22.1M |
| 37 | Hy1.5-Distill-Modelslightx2v | Text to Video | 2 | — | 31 | — |
| 38 | public-poetry-50mwildfellhall | Text Generation | 2 | — | 3 | 46.7M |
| 39 | IndustryLLMalibaba-multimodal-industrial-ai | Text Generation | 2 | — | 3 | 35.1B |
| 40 | LongCat-Videomeituan-longcat | Text to Video | 2 | ▲2.7%(up) | 585 | — |
| 41 | vdn-minimax-h3OpenVDN | Text to Video | 2 | — | 335 | — |
| 42 | h3-vbvrPatarapoom | Image To Video | 2 | ▲19.1%(up) | 11 | — |
| 43 | uno-qwen3-8Bs-sahoo | Text Generation | 2 | ▲114.9%(up) | 4 | 8.2B |
| 44 | TiRex-2NX-AI | Time Series Forecasting | 2 | ▲75.3%(up) | 48 | 82.5M |
| 45 | Kandinsky-6.0-Pro-5s-Diffuserskandinskylab | Image To Video | 2 | — | 62 | 30.1B |
| 46 | VibeVoice-ASR-Streaming-1.5Bmicrosoft | Speech Recognition | 2 | ▲47.2%(up) | 63 | 2.8B |
| 47 | T5Gemma-TTS-2b-2bAratako | Text to Speech | 2 | ▲0.9%(up) | 124 | 5.3B |
| 48 | manaca-1b-baseAIInstituteLNCC | Text Generation | 2 | — | 43 | 1.7B |
| 49 | deepseek-coder-1.3b-instructdeepseek-ai | Text Generation | 2 | ▲0.3%(up) | 203 | 1.3B |
| 50 | Ornith-1.5-9B-uncensoredjunafinity | Image Text to Text | 2 | — | 12 | 9.4B |