239 modèles dans 42 catégories | Généré le 08/10/2026 22:33 UTC
239 modèles sélectionnés
| # | Modele | DL/Jour | Params | pipeline | FR |
|---|---|---|---|---|---|
| 1 | Comfy-Org/MiniMax-H3 | 337,484 | — | image-to-image | — |
| 2 | Comfy-Org/Qwen-Image-2.1 FR | 324,889 | — | image-to-image | ✓ |
| 3 | prism-ml/Ternary-Bonsai-2-27B-gguf | 206,924 | 27.0B (GGUF) | text-generation | — |
| 4 | autotrust/JEV-27B-VL | 191,629 | 27.8B | image-text-to-text | — |
| 5 | autotrust/GEV-26B-Decide | 150,644 | 25.8B | text-classification | — |
| 6 | zai-org/GLM-5.3-Flash FR | 144,382 | 321.3B | image-text-to-text | ✓ |
| 7 | sentence-transformers/all-MiniLM-L6-v2 | 138,242 | 23.0MB | sentence-similarity | — |
| 8 | unsloth/Qwen3.8-27B-GGUF FR | 116,408 | 27.0B (GGUF) | conversational | ✓ |
| 9 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR | 109,853 | GGUF (inconnu) | image-text-to-text | ✓ |
| 10 | abenzerps/Qwen-Image-2.1-Uncensored-GGUF FR | 107,393 | GGUF (inconnu) | text-to-image | ✓ |
| 11 | Qwen/Qwen3.8-27B FR | 106,901 | 27.8B | image-text-to-text | ✓ |
| 12 | ornith-ai/Ornith-1.5-9B-GGUF | 102,935 | 9.0B (GGUF) | text-generation | — |
| 13 | SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR | 102,068 | GGUF (inconnu) | image-text-to-text | ✓ |
| 14 | mudler/locate-anything.cpp-gguf | 101,373 | GGUF (inconnu) | object-detection | — |
| 15 | Qwen/Qwen3.8-27B-FP8 FR | 83,325 | 27.8B | image-text-to-text | ✓ |
| 16 | audio-cpp/audio.cpp-gguf | 72,418 | GGUF (inconnu) | text-to-speech | — |
| 17 | ornith-ai/Ornith-1.5-35B-A3B-GGUF | 72,137 | 35.0B (GGUF) (MOE) MOE | text-generation | — |
| 18 | Comfy-Org/Krea-2 | 65,822 | — | image-to-image | — |
| 19 | deepseek-ai/DeepSeek-V4-Flash-0731 FR | 65,516 | 304.2B | text-generation | ✓ |
| 20 | amazon/chronos-2 | 63,040 | 0.1B | time-series-forecasting | — |
| 21 | Qwen/Qwen3-0.6B FR | 58,887 | 0.8B | text-generation | ✓ |
| 22 | google/gemma-4-26B-A4B-it FR | 58,131 | 25.8B / 4.0B MOE | image-text-to-text | ✓ |
| 23 | DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF FR | 55,066 | 27.0B (GGUF) | image-text-to-text | ✓ |
| 24 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF FR | 49,989 | GGUF (inconnu) | image-text-to-text | ✓ |
| 25 | MiniMaxAI/MiniMax-H3 | 49,856 | 33.1B | image-text-to-video | — |
| 26 | cross-encoder/ms-marco-MiniLM-L6-v2 | 49,110 | 23.0MB | text-ranking | — |
| 27 | unsloth/Qwen-Image-2.1-GGUF FR | 47,380 | GGUF (inconnu) | text-to-image | ✓ |
| 28 | deepseek-ai/DeepSeek-V4.1-Flash FR | 45,804 | 763.2B | image-text-to-text | ✓ |
| 29 | ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF FR | 44,308 | 27.0B (GGUF) | text-generation | ✓ |
| 30 | JonathanColetti/Qwen3.8-27B-Uncensored-GGUF FR | 42,964 | 27.0B (GGUF) | text-generation | ✓ |
| 31 | openbmb/MiniCPM5-2B | 39,520 | 2.5B | text-generation | — |
| 32 | nvidia/Qwen3.6-35B-A3B-NVFP4 FR | 39,222 | 18.7B / 3.0B MOE | text-generation | ✓ |
| 33 | unsloth/Qwen3.8-27B-NVFP4 FR | 38,772 | 19.9B | other | ✓ |
| 34 | zai-org/GLM-5.3 FR | 35,134 | 753.3B | text-generation | ✓ |
| 35 | BAAI/bge-m3 FR | 34,203 | — | sentence-similarity | ✓ |
| 36 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 FR | 29,703 | 0.1B | sentence-similarity | ✓ |
| 37 | google/timesfm-3.0-pytorch | 27,663 | 0.3B | time-series-forecasting | — |
| 38 | Comfy-Org/z_image_turbo | 27,563 | — | image-to-image | — |
| 39 | unsloth/MiniMax-H3-GGUF | 27,488 | GGUF (inconnu) | image-text-to-video | — |
| 40 | mradermacher/Ornith-1.5-9B-uncensored-GGUF | 27,339 | 9.0B (GGUF) | conversational | — |
| 41 | lightx2v/Minimax-h3-Turbo | 24,408 | — | image-to-video | — |
| 42 | FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree | 23,046 | 35.0B | text-to-video | — |
| 43 | google-bert/bert-base-uncased | 22,365 | 0.1B | fill-mask | — |
| 44 | Lightricks/LTX-2.5 FR | 21,933 | — | image-to-video | ✓ |
| 45 | autotrust/JEV-9B | 21,754 | 9.0B | text-classification | — |
| 46 | Viggle/Qwen-Image-2.1-viggle-turbo FR | 21,558 | 7.1B | text-to-image | ✓ |
| 47 | google/gemma-4-E4B-it FR | 19,909 | 8.0B | any-to-any | ✓ |
| 48 | PrunaAI/Pruna-Qwen-Image-2.1 FR | 19,094 | — | text-to-image | ✓ |
| 49 | Qwen/Qwen3-Embedding-0.6B FR | 18,255 | 0.6B | feature-extraction | ✓ |
| 50 | mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF | 18,092 | 9.0B (GGUF) | conversational | — |
| 51 | MATLOWAI/minimax-h3-fused-turbo-int8-convrot | 17,992 | — | image-text-to-video | — |
| 52 | WarmBloodAban/Minimax-h3_Singularity | 17,809 | — | image-to-video | — |
| 53 | hexgrad/Kokoro-82M | 17,035 | — | text-to-speech | — |
| 54 | Mapika/decider-2b | 15,006 | 1.9B | text-classification | — |
| 55 | Comfy-Org/Wan_2.2_ComfyUI_Repackaged | 14,855 | — | image-to-video | — |
| 56 | unsloth/embeddinggemma-2-GGUF FR | 14,846 | GGUF (inconnu) | feature-extraction | ✓ |
| 57 | google-t5/t5-small FR | 14,549 | 61.0MB | translation | ✓ |
| 58 | google/gemma-4-E2B-it FR | 13,612 | 5.1B | any-to-any | ✓ |
| 59 | nomic-ai/nomic-embed-text-v1.5 | 13,411 | 0.1B | sentence-similarity | — |
| 60 | autotrust/JEV-27B | 13,379 | 26.9B | text-classification | — |
| 61 | FastVideo/FastVideo-FastH3-Comfy | 13,184 | — | image-to-image | — |
| 62 | pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF | 12,275 | GGUF (inconnu) | image-to-image | — |
| 63 | google/gemma-4-12B-it FR | 12,240 | 12.0B | any-to-any | ✓ |
| 64 | openai/clip-vit-base-patch32 | 12,046 | — | zero-shot-image-classification | — |
| 65 | Comfy-Org/YuE2 | 11,365 | — | image-to-image | — |
| 66 | pyannote/speaker-diarization-community-1 | 10,280 | — | automatic-speech-recognition | — |
| 67 | Comfy-Org/Ming-Image | 9,899 | — | image-to-image | — |
| 68 | BAAI/bge-large-en-v1.5 | 9,001 | 0.3B | feature-extraction | — |
| 69 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice FR | 8,909 | 1.9B | text-to-speech | ✓ |
| 70 | ornith-ai/Ornith-1.5-35B-A3B-DFlash | 8,871 | 0.4B / 3.0B MOE | other | — |
| 71 | nvidia/nemotron-3.5-asr-streaming-0.6b FR | 8,835 | 0.6B | automatic-speech-recognition | ✓ |
| 72 | openai/whisper-large-v3-turbo FR | 8,707 | 0.8B | automatic-speech-recognition | ✓ |
| 73 | BAAI/bge-base-en-v1.5 | 8,600 | 0.1B | feature-extraction | — |
| 74 | google/embeddinggemma-300m FR | 8,104 | 0.3B | sentence-similarity | ✓ |
| 75 | nvidia/Cosmos3-Edge | 7,907 | 3.9B | other | — |
| 76 | FastVideo/FastVideo-FastH3-Trim-Comfy | 7,814 | — | image-to-image | — |
| 77 | k2-fsa/OmniVoice FR | 7,552 | 0.6B | text-to-speech | ✓ |
| 78 | mistralai/Voxtral-Mini-4B-Realtime-2602 FR | 7,369 | 4.4B | automatic-speech-recognition | ✓ |
| 79 | zai-org/GLM-OCR FR | 7,346 | 1.3B | image-to-text | ✓ |
| 80 | litert-community/gemma-4-E2B-it-litert-lm FR | 7,253 | 2.0B | other | ✓ |
| 81 | Comfy-Org/Pixal3D | 6,960 | — | image-to-image | — |
| 82 | onnx-community/embeddinggemma-2-ONNX FR | 6,904 | — | feature-extraction | ✓ |
| 83 | google/vit-base-patch16-224 | 6,897 | 87.0MB | image-classification | — |
| 84 | pyannote/speaker-diarization-3.1 | 6,745 | — | automatic-speech-recognition | — |
| 85 | Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1 FR | 6,733 | — | text-to-image | ✓ |
| 86 | autotrust/GEV-26B-Decide-NVFP4 | 6,552 | 14.4B | text-classification | — |
| 87 | facebook/sam3 | 6,484 | 0.9B | mask-generation | — |
| 88 | unsloth/Qwen-Image-2.1-FP8 FR | 6,351 | — | text-to-image | ✓ |
| 89 | google/gemma-4-12B-it-qat-q4_0-gguf FR | 6,243 | 12.0B (GGUF) | any-to-any | ✓ |
| 90 | coqui/XTTS-v2 | 6,216 | — | text-to-speech | — |
| 91 | ornith-ai/Ornith-1.5-9B-DFlash | 6,172 | 1.3B | other | — |
| 92 | microsoft/TRELLIS.2-4B FR | 6,093 | 4.0B | image-to-3d | ✓ |
| 93 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 FR | 5,891 | 0.3B | sentence-similarity | ✓ |
| 94 | fastino/GLiNER2.5-Decide | 5,168 | 0.5B | text-classification | — |
| 95 | Abiray/Qwen-Image-2.1-GGUF FR | 5,100 | GGUF (inconnu) | text-to-image | ✓ |
| 96 | Qwen/Qwen3-ASR-1.7B FR | 5,009 | 2.3B | automatic-speech-recognition | ✓ |
| 97 | ibm-granite/granite-4.2-8b-GGUF | 4,949 | 8.0B (GGUF) | conversational | — |
| 98 | Qwen/Qwen-Image-2.1 FR | 4,873 | 7.1B | text-to-image | ✓ |
| 99 | pyannote/segmentation-3.0 | 4,861 | — | voice-activity-detection | — |
| 100 | ggml-org/embeddinggemma-2-GGUF FR | 4,759 | GGUF (inconnu) | feature-extraction | ✓ |
| 101 | fastino/gliner2.5-multi-v1 FR | 4,676 | 0.3B | other | ✓ |
| 102 | Lightricks/LTX-2.3 FR | 4,661 | — | image-to-video | ✓ |
| 103 | Qwen/Qwen3-VL-Embedding-2B FR | 4,122 | 2.1B | sentence-similarity | ✓ |
| 104 | Winnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI | 4,064 | — | image-to-video | — |
| 105 | unsloth/gemma-4-12B-it-qat-GGUF FR | 4,000 | 12.0B (GGUF) | any-to-any | ✓ |
| 106 | pottokao/Qwen-Image-2.1-PE-I2I-Heretic-GGUF FR | 3,740 | GGUF (inconnu) | conversational | ✓ |
| 107 | stabilityai/stable-diffusion-xl-base-1.0 | 3,730 | 2.6B | text-to-image | — |
| 108 | openai/whisper-large-v3 FR | 3,695 | 1.5B | automatic-speech-recognition | ✓ |
| 109 | tencent/Hy-MT2-7B-GGUF | 3,573 | 7.0B (GGUF) | conversational | — |
| 110 | mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-GGUF FR | 3,416 | GGUF (inconnu) | conversational | ✓ |
| 111 | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive FR | 3,293 | 9.0B | conversational | ✓ |
| 112 | larryvrh/MiniMax-H3-Turbo-Lora | 3,258 | — | text-to-video | — |
| 113 | Qwen/Qwen3-ASR-1.7B-hf FR | 3,237 | 2.0B | automatic-speech-recognition | ✓ |
| 114 | drbaph/MiniMax-H3-Turbo-Lora-ComfyUI | 3,188 | — | text-to-video | — |
| 115 | unsloth/gemma-4-E4B-it-qat-GGUF FR | 3,138 | 4.0B (GGUF) | any-to-any | ✓ |
| 116 | QuantFunc/Minimax-H3-Quantfunc-4bit | 3,136 | 4.0B | text-to-video | — |
| 117 | openbmb/VoxCPM2 FR | 3,024 | 2.3B | text-to-speech | ✓ |
| 118 | google/gemma-4-E4B FR | 2,829 | 8.0B | any-to-any | ✓ |
| 119 | nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF FR | 2,663 | 27.0B (GGUF) | conversational | ✓ |
| 120 | 0xSojalSec/Qwen-Image-2.1-Uncensored-GGUF FR | 2,632 | GGUF (inconnu) | text-to-image | ✓ |
| 121 | litert-community/embeddinggemma-2-740m-litert-lm FR | 2,519 | — | other | ✓ |
| 122 | Edge0/Audio8-ASR-Infinite | 2,387 | 4.1B | automatic-speech-recognition | — |
| 123 | Qwen/Qwen3-TTS-12Hz-0.6B-Base FR | 2,272 | 0.9B | text-to-speech | ✓ |
| 124 | ggml-org/Bespoke-Nimble-9B-v3-GGUF | 2,256 | 9.0B (GGUF) | zero-shot-classification | — |
| 125 | ai-sage/GigaAM-v3 | 2,234 | — | automatic-speech-recognition | — |
| 126 | tencent/Hy-MT2-1.8B-GGUF | 2,205 | 1.8B (GGUF) | conversational | — |
| 127 | akatz-ai/MiniMax-H3-Character-Swap-LoRA | 2,173 | — | video-to-video | — |
| 128 | bartowski/TheDrummer_Artemis-31B-v1.2-GGUF | 2,034 | 31.0B (GGUF) | any-to-any | — |
| 129 | autotrust/JEV-Gemma4-26B-A4B FR | 1,839 | 25.8B / 4.0B MOE | text-classification | ✓ |
| 130 | convaiinnovations/laya | 1,816 | 0.4B | text-classification | — |
| 131 | Serveurperso/Qwen3-TTS-GGUF FR | 1,812 | GGUF (inconnu) | text-to-speech | ✓ |
| 132 | nvidia/Nemotron-3-Diarization | 1,785 | 99.0MB | voice-activity-detection | — |
| 133 | Lucebox/DeepSeek-V4.1-Flash-ROCMFP23-GGUF FR | 1,784 | GGUF (inconnu) | other | ✓ |
| 134 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,724 | 0.3B | image-feature-extraction | — |
| 135 | microsoft/VibeVoice-1.5B FR | 1,723 | 2.7B | text-to-speech | ✓ |
| 136 | speach1sdef178/MiniMax-H3-X2-Detail-VAE | 1,700 | — | image-to-video | — |
| 137 | IndexTeam/Index-Translate-9B-GGUF | 1,616 | 9.0B (GGUF) | translation | — |
| 138 | Mapika/decider-4b | 1,578 | 4.2B | text-classification | — |
| 139 | OpenMOSS-Team/MOSS-Transcribe-Diarize FR | 1,524 | 0.9B | audio-text-to-text | ✓ |
| 140 | turboderp/Qwen3.8-27B-exl3 FR | 1,445 | 27.0B | other | ✓ |
| 141 | ggml-org/Laya-GGUF | 1,445 | GGUF (inconnu) | text-classification | — |
| 142 | madebyollin/texture-fix-vae-for-qwen-image-2.1 FR | 1,387 | 0.3B | other | ✓ |
| 143 | fal/MiniMax-H3-Realism-People-LoRA | 1,385 | — | image-text-to-video | — |
| 144 | canberkkkkkk/ema-lightning | 1,352 | — | text-to-speech | — |
| 145 | alibaba-pai/MiniMax-H3-Acc-LoRAs | 1,271 | — | text-to-video | — |
| 146 | m-a-p/YuE2-3B | 1,258 | 3.6B | text-to-audio | — |
| 147 | facebook/dinov3-vitb16-pretrain-lvd1689m | 1,202 | 86.0MB | image-feature-extraction | — |
| 148 | alibaba-pai/MiniMax-H3-Fun-Controlnet-Union-2.0 | 1,201 | — | text-to-video | — |
| 149 | google/gemma-4-E2B FR | 1,094 | 5.1B | any-to-any | ✓ |
| 150 | drbaph/Hyperflow-Comfyui | 1,035 | — | image-text-to-video | — |
| 151 | pablodawson/MiniMax-H3-360-Orbit-LoRA | 1,034 | — | image-text-to-video | — |
| 152 | QuantStack/Wan2.2-I2V-A14B-GGUF | 990 | 14.0B (GGUF) | image-to-video | — |
| 153 | IndexTeam/Index-Translate-2B-GGUF | 971 | 2.0B (GGUF) | translation | — |
| 154 | ibm-granite/granite-embedding-311m-multilingual-r2 FR | 970 | 0.3B | feature-extraction | ✓ |
| 155 | Lightricks/LTX-Video | 967 | 1.9B | image-to-video | — |
| 156 | Abiray/LTX-2.5-Distilled-GGUF FR | 958 | GGUF (inconnu) | text-to-video | ✓ |
| 157 | google/embeddinggemma-2 FR | 881 | 0.7B | feature-extraction | ✓ |
| 158 | m-a-p/SheetSage2 | 871 | 57.0MB | feature-extraction | — |
| 159 | google/gemma-4-12B FR | 770 | 12.0B | any-to-any | ✓ |
| 160 | Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details | 714 | 22.0B | video-to-video | — |
| 161 | unsloth/embeddinggemma-2 FR | 698 | 0.7B | feature-extraction | ✓ |
| 162 | pixai-labs/pixai-tagger-v1.0 | 685 | 0.5B | image-classification | — |
| 163 | nvidia/personaplex-7b-v1 | 654 | 8.4B | audio-to-audio | — |
| 164 | Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen | 640 | 22.0B | video-to-video | — |
| 165 | SulphurAI/Sulphur-2-base | 640 | — | text-to-video | — |
| 166 | facebook/dinov3-vits16-pretrain-lvd1689m | 638 | 22.0MB | image-feature-extraction | — |
| 167 | Lightricks/LTX-2.5-Diffusers FR | 630 | 19.0B | text-to-video | ✓ |
| 168 | realrebelai/LTX-2.5_GGUFs | 610 | GGUF (inconnu) | text-to-video | — |
| 169 | IndexTeam/Index-Translate-35B-A3B-preview-GGUF | 595 | 35.0B (GGUF) (MOE) MOE | translation | — |
| 170 | briaai/RMBG-2.0 | 593 | 0.2B | image-segmentation | — |
| 171 | manjunathshiva/opendecider-nano | 572 | 0.4B | zero-shot-classification | — |
| 172 | mlx-community/clef-flash-4bit | 543 | 9.4B | zero-shot-classification | — |
| 173 | Viggle/Viggle-Animate | 510 | 33.1B | video-to-video | — |
| 174 | ggml-org/lev-GGUF | 509 | GGUF (inconnu) | zero-shot-classification | — |
| 175 | Jojocodex/wushu-action-v7-minimax-h3-fl2va-ref2va-lora | 465 | — | image-to-video | — |
| 176 | LiquidAI/LFM2.5-Encoder-350M FR | 438 | 0.4B | fill-mask | ✓ |
| 177 | stabilityai/stable-audio-3-medium | 429 | 2.3B | text-to-audio | — |
| 178 | Lightricks/LTX-2.5-22b-IC-LoRA-SDR-To-HDR | 415 | 22.0B | video-to-video | — |
| 179 | videorebirth/hyperflow | 393 | — | image-text-to-video | — |
| 180 | Prior-Labs/tabpfn_3_5 | 379 | — | tabular-classification | — |
| 181 | czl/CLM-v0.1-8B-GGUF | 373 | 8.0B (GGUF) | text-ranking | — |
| 182 | openjev/openjev FR | 318 | 27.4B | zero-shot-classification | ✓ |
| 183 | Lightricks/LTX-2.5-22b-IC-LoRA-Restore | 315 | 22.0B | video-to-video | — |
| 184 | Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients | 272 | 22.0B | video-to-video | — |
| 185 | ACE-Step/Ace-Step1.5 | 265 | — | text-to-audio | — |
| 186 | vllm-sr/Decision-2.0-Vega-27B | 260 | 27.0B | zero-shot-classification | — |
| 187 | facebook/sam3.1 | 256 | — | mask-generation | — |
| 188 | stabilityai/stable-audio-3-small-sfx | 255 | 0.6B | text-to-audio | — |
| 189 | jeff-legacy/Jeff-Qwen3.5-0.8B FR | 254 | 0.9B | zero-shot-classification | ✓ |
| 190 | Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render | 251 | 22.0B | video-to-video | — |
| 191 | Contrastive-LM/CLM-v0.1-8B | 245 | 8.0B | text-ranking | — |
| 192 | jhu-clsp/mmBERT-small | 235 | — | fill-mask | — |
| 193 | lerobot/smolvla_base | 230 | 0.5B | robotics | — |
| 194 | tencent/Hy-MT2-1.8B FR | 216 | 2.0B | translation | ✓ |
| 195 | PSRben/VisionHOPE | 202 | — | image-classification | — |
| 196 | mlx-community/clef-4bit | 194 | 27.4B | zero-shot-classification | — |
| 197 | mlx-community/clef-8bit | 181 | 27.4B | zero-shot-classification | — |
| 198 | Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler | 147 | 22.0B | video-to-video | — |
| 199 | facebook/dinov3-vitl16-pretrain-sat493m | 127 | 0.3B | image-feature-extraction | — |
| 200 | tencent/Hunyuan3D-2.1 | 124 | — | image-to-3d | — |
| 201 | vllm-sr/Decision-2.0-Kai-0.6B | 118 | 0.6B | zero-shot-classification | — |
| 202 | MiniMaxAI/MiniMax-Music3 | 116 | 2.4B | text-to-audio | — |
| 203 | MahmoodLab/UNI2-h | 111 | — | image-feature-extraction | — |
| 204 | IndexTeam/Index-Translate-2B | 109 | 2.3B | translation | — |
| 205 | black-forest-labs/flux-3-action-so101 FR | 103 | 6.9B | robotics | ✓ |
| 206 | IndexTeam/Index-Translate-9B | 102 | 9.7B | translation | — |
| 207 | Ultralytics/YOLO26 FR | 73 | — | object-detection | ✓ |
| 208 | black-forest-labs/flux-3-action-droid FR | 72 | 6.9B | robotics | ✓ |
| 209 | Lightricks/LTX-2.5-22b-IC-LoRA-Day-To-Night | 66 | 22.0B | video-to-video | — |
| 210 | mistralai/Voxtral-Small-24B-2507 FR | 54 | 24.3B | audio-text-to-text | ✓ |
| 211 | black-forest-labs/flux-3-action-base FR | 52 | — | robotics | ✓ |
| 212 | MahmoodLab/UNI | 52 | — | image-feature-extraction | — |
| 213 | nvidia/RE-USE | 44 | 10.0MB | audio-to-audio | — |
| 214 | neuphonic/neudecide | 36 | — | audio-classification | — |
| 215 | stabilityai/stable-fast-3d | 33 | 1.0B | image-to-3d | — |
| 216 | birlaailabs/yug | 27 | 0.3B | time-series-forecasting | — |
| 217 | nlpai-lab/RenderRank-2B | 26 | 2.1B | text-ranking | — |
| 218 | stabilityai/stable-audio-open-1.0 | 22 | 1.2B | text-to-audio | — |
| 219 | interfaze-ai/interfaze-1-lite FR | 21 | — | image-text-to-image | ✓ |
| 220 | MCG-NJU/OneStreamer-4B | 17 | 4.4B | video-text-to-text | — |
| 221 | Modotte/AIRealNet-Audio FR | 15 | 95.0MB | audio-classification | ✓ |
| 222 | nvidia/music-flamingo-hf | 14 | 8.3B | audio-text-to-text | — |
| 223 | desert-ant-labs/clear | 12 | — | audio-to-audio | — |
| 224 | LiquidAI/LFM2.5-Encoder-350M-GGUF FR | 9 | GGUF (inconnu) | fill-mask | ✓ |
| 225 | facebook/VGGT-1B-Commercial | 7 | 1.3B | image-to-3d | — |
| 226 | LiquidAI/LFM2.5-Encoder-230M-GGUF FR | 5 | GGUF (inconnu) | fill-mask | ✓ |
| 227 | nvidia/Lyra-2.0 | 4 | — | image-to-3d | — |
| 228 | google/tabfm-1.1.0-pytorch | 3 | — | tabular-classification | — |
| 229 | StanfordAIMI/stanford-deidentifier-with-radiology-reports-and-i2b2 | 2 | 2.0B | token-classification | — |
| 230 | MeteoSwiss/Varda-single-1.0 | 0 | — | graph-ml | — |
| 231 | NU-World-Model-Embodied-AI/phyjudge-9B | 0 | 9.0B | video-text-to-text | — |
| 232 | nvidia/PixelUMM | 0 | — | image-to-text | — |
| 233 | niclasclassen/robustness-of-transferability-estimation-metrics-for-medical-imaging | 0 | — | image-classification | — |
| 234 | TencentARC/Pixal3D | 0 | — | image-to-3d | — |
| 235 | spellbrush/kyaraembed | 0 | — | audio-classification | — |
| 236 | marcelosantoskuw/paper_015153151_visual_question_answering | 0 | — | visual-question-answering | — |
| 237 | christianhof/paper_015561242_visual_question_answering | 0 | — | visual-question-answering | — |
| 238 | huawei-bayerlab/marigold-v2-0 | 0 | — | depth-estimation | — |
| 239 | nvidia/c-fast-foundationstereo | 0 | — | depth-estimation | — |