| 1 | INT4-Convrot-Comfy-ModelsWinnougan | — | 4 | — | 63 | — |
| 2 | Qwen3.8-27B-NVFP4RedHatAI | — | 4 | — | 4 | 19.9B |
| 3 | Qwen3.8-27B-MTPLX-Optimized-Quality-FP16Youssofal | Text Generation | 4 | — | 9 | 8B |
| 4 | Ornith-1.5-9B-uncensored-i1-GGUFmradermacher | — | 4 | — | 6 | — |
| 5 | Orion-26B-A4B-v1d-GGUFBeaverAI | — | 4 | — | 4 | — |
| 6 | Wan_2.2_ComfyUI_RepackagedComfy-Org | Image To Video | 4 | — | 846 | — |
| 7 | Kimi-K3-DSparkRadixArk | Text Generation | 4 | — | 54 | 2.2B |
| 8 | krea2-outpaintyijunwang2 | Image To Image | 4 | — | 42 | — |
| 9 | Qwen3.6-27B-GGUFunsloth | Image Text to Text | 4 | — | 947 | — |
| 10 | barksuno | Text to Speech | 4 | — | 1,558 | — |
| 11 | diffusiongemma-26B-A4B-it-NVFP4nvidia | Text Generation | 4 | — | 122 | 14.4B |
| 12 | Qwen3.6-35B-A3B-speculator.dsparkRedHatAI | — | 4 | — | 15 | 950M |
| 13 | RMBG-1.4briaai | Image Segmentation | 4 | — | 2,016 | 44.1M |
| 14 | Qwen3.6-35B-A3B-APEX-GGUFmudler | — | 4 | — | 195 | — |
| 15 | Z-Image-LoranphSi | Text to Image | 4 | — | 144 | — |
| 16 | medasrgoogle | Speech Recognition | 4 | — | 358 | 105M |
| 17 | Qwen3-Embedding-0.6B-GGUFQwen | — | 4 | — | 566 | — |
| 18 | F5-TTS_RUSSIANMisha24-10 | Text to Speech | 4 | — | 221 | — |
| 19 | GR00T-N1.7-3Bnvidia | Robotics | 4 | — | 112 | 3.1B |
| 20 | MOSS-TTSOpenMOSS-Team | Text to Speech | 4 | — | 425 | 8.5B |
| 21 | Huihui-Qwen3.8-27B-abliterated-mlx-4BitAutisticAF | Image Text to Text | 4 | — | 4 | 4.2B |
| 22 | Omega-Convergence-27B-v1.0-I-Compact-MXFP4_ALPHA_TESTINGPhil2Sat | — | 4 | — | 4 | — |
| 23 | Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-AggressiveHauhauCS | — | 4 | — | 21 | — |
| 24 | LTX-2.5-22b-IC-LoRA-Pixel-Spatial-UpscalerLightricks | Video To Video | 4 | — | 44 | — |
| 25 | LLaDA2.2-flashinclusionAI | Text Generation | 4 | — | 82 | 103B |
| 26 | Ornith-1.5-35B-A3B-Abliterated-MLX-4bitPocketAiHub | Image Text to Text | 4 | — | 4 | 5.9B |
| 27 | JoyAI-Echojdopensource | Text to Video | 4 | — | 172 | — |
| 28 | LTX-Best-Face-IDAlissonerdx | Text to Video | 4 | — | 312 | — |
| 29 | Krea-2-depth-controlnetPatil | Image To Image | 4 | — | 139 | — |
| 30 | Flash-Attention-2_for_Windowsussoewwin | — | 4 | — | 134 | — |
| 31 | SillyTavern-Presets-Sphiratriothsphiratrioth666 | — | 4 | — | 313 | — |
| 32 | Qwen3.8-27B-PrismaAQUA-5.5bit-vllmrdtand | Image Text to Text | 4 | — | 26 | 19.1B |
| 33 | Z-Image-Turbo-AIOSeeSee21 | Text to Image | 4 | — | 291 | — |
| 34 | gpt2openai-community | Text Generation | 4 | — | 3,413 | 137M |
| 35 | Qwen3.8-27B-IQ4-XS-MTP-16GB-VRAM-GGUFBucoid | — | 4 | — | 7 | — |
| 36 | Qwen3.8-9B-Distill-uncensored-heretic-Q4_K_M-GGUFge525 | Text Generation | 4 | — | 4 | — |
| 37 | Qwen3.8-27B-MLX-8bitlmstudio-community | Image Text to Text | 4 | — | 12 | 8B |
| 38 | DeepSeek-R1-Distill-Qwen-32Bdeepseek-ai | Text Generation | 4 | — | 1,599 | 32.8B |
| 39 | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16nvidia | Text Generation | 4 | — | 329 | 561B |
| 40 | Qwen3.8_4B_Distilled_GGUFMa7ee7 | Text Generation | 4 | — | 33 | — |
| 41 | UI-TARS-1.5-7BByteDance-Seed | Image Text to Text | 4 | — | 595 | 8.3B |
| 42 | GOT-OCR2_0stepfun-ai | Image Text to Text | 4 | — | 1,554 | 716M |
| 43 | Qwen3.8-Distill-35B-A3B-Coder-AbliteratedLord-H4D3ZS | Text Generation | 4 | — | 5 | — |
| 44 | Qwen3-Omni-30B-A3B-InstructQwen | Any to Any | 4 | — | 987 | 35.3B |
| 45 | Qwen3.8-27B-bf16mlx-community | Image Text to Text | 4 | — | 22 | 27.4B |
| 46 | Ornith-1.5-397B-GGUFbartowski | Image Text to Text | 4 | — | 4 | — |
| 47 | Ornith-1.5-35B-A3B-Abliterated-MTP-UD-APEX-GGUFgbuzhf | Image Text to Text | 4 | — | 4 | — |
| 48 | Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTPDavidAU | Image Text to Text | 4 | — | 18 | 9.7B |
| 49 | GRM-3.2-SkyOrionLLM | Image Text to Text | 4 | — | 45 | 35.1B |
| 50 | Qwen3.8-27B-Uncensored-NInferfullmetaljackass | Image Text to Text | 4 | — | 4 | — |