176 modèles dans 39 catégories | Généré le 20/11/2026 23:33 UTC
176 modèles sélectionnés
| # | Modele | DL/Jour | Params | pipeline | FR |
|---|---|---|---|---|---|
| 1 | Comfy-Org/MiniMax-H3 | 294,239 | ≈33.1B | image-to-image | |
| 2 | Comfy-Org/MiniMax-H3-Image | 285,336 | ≈20.1B | text-to-image | |
| 3 | Comfy-Org/MOSS-Image | 170,524 | ≈9.7B | image-to-image | |
| 4 | ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF FR | 159,382 | GGUF (inconnu) | text-generation | ✓ |
| 5 | Comfy-Org/Qwen-Image-2.1 FR | 142,687 | ≈8.8B | text-to-image | ✓ |
| 6 | mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF FR | 121,765 | 9.0B (GGUF) | text-generation | ✓ |
| 7 | ai-coustics/quail-voice-focus | 103,710 | — | audio-to-audio | |
| 8 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR | 100,499 | GGUF (inconnu) | image-text-to-text | ✓ |
| 9 | sentence-transformers/all-MiniLM-L6-v2 | 97,147 | 23.0MB | sentence-similarity | |
| 10 | SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR | 88,131 | GGUF (inconnu) | image-text-to-text | ✓ |
| 11 | Efficient-Large-Model/Open-H3-Regenerate-2K | 85,019 | — | video-to-video | |
| 12 | unsloth/Qwen3.8-27B-GGUF FR | 74,578 | ≈24.4B | text-generation | ✓ |
| 13 | zai-org/GLM-5.3-Flash FR | 73,539 | 321.3B | image-text-to-text | ✓ |
| 14 | Qwen/Qwen3.8-27B-FP8 FR | 65,727 | 27.8B | image-text-to-text | ✓ |
| 15 | ornith-ai/Ornith-1.5-9B-GGUF | 61,732 | 9.0B (GGUF) | text-generation | |
| 16 | Qwen/Qwen3.8-27B FR | 60,322 | 27.8B | image-text-to-text | ✓ |
| 17 | PrunaAI/P-Image-OSS-Comfy | 56,178 | ≈20.2B | text-to-image | |
| 18 | Hearthscale/MiniMax-H3-Image-GGUF | 55,262 | GGUF (inconnu) | text-to-image | |
| 19 | MiniMaxAI/MiniMax-H3-Image | 51,587 | ≈2.9B | text-to-image | |
| 20 | MiniMaxAI/MiniMax-H3 FR | 50,018 | 33.1B | image-text-to-video | ✓ |
| 21 | mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF FR | 49,872 | 9.0B (GGUF) | text-generation | ✓ |
| 22 | VideoRebirthAI/hyperflow-h3-flash | 49,669 | — | image-text-to-video | |
| 23 | unsloth/DeepSeek-V4.1-Flash-1017-GGUF FR | 46,890 | GGUF (inconnu) | image-text-to-text | ✓ |
| 24 | unsloth/Qwen-Image-2.1-Turbo-GGUF FR | 45,369 | GGUF (inconnu) | text-to-image | ✓ |
| 25 | ornith-ai/Ornith-1.5-35B-A3B-GGUF | 43,574 | 35.0B (GGUF) · MoE MOE | text-generation | |
| 26 | BAAI/bge-small-en-v1.5 | 37,444 | 33.0MB | feature-extraction | |
| 27 | unsloth/MiniMax-H3-GGUF | 32,763 | GGUF (inconnu) | image-text-to-video | |
| 28 | BAAI/bge-m3 FR | 32,219 | ≈0.6B | sentence-similarity | ✓ |
| 29 | Comfy-Org/Z-Image-Turbo | 27,781 | ≈6.2B | image-to-image | |
| 30 | black-forest-labs/flux-3-image-klein-comfy FR | 26,520 | ≈9.4B | image-to-image | ✓ |
| 31 | Lightricks/LTX-2.5 FR | 24,704 | ≈21.0B | image-to-video | ✓ |
| 32 | LiquidAI/LFM3-Omni-2B-GGUF FR | 22,189 | 2.0B (GGUF) | any-to-any | ✓ |
| 33 | Comfy-Org/Wan-2.2 | 21,011 | ≈17.3B | image-to-video | |
| 34 | OliviaRossi/Minimax-h3_Singularity-x-10Eros-Max_PRISM | 20,676 | ≈33.1B | other | |
| 35 | hexgrad/Kokoro-82M | 19,093 | 82.0M | text-to-speech | |
| 36 | Comfy-Org/RelayVSR | 18,919 | ≈5.2B | unconditional-image-generation | |
| 37 | k2-fsa/OmniVoice FR | 18,244 | 0.6B | text-to-speech | ✓ |
| 38 | lightx2v/Minimax-h3-Turbo | 17,326 | ≈34.0B | image-to-image | |
| 39 | WarmBloodAban/Minimax-h3_Singularity | 17,126 | ≈33.1B | image-to-video | |
| 40 | google/gemma-4-E4B-it FR | 16,452 | 8.0B | any-to-any | ✓ |
| 41 | Qwen/Qwen3-TTS-12Hz-1.7B-Base FR | 13,648 | 1.9B | text-to-speech | ✓ |
| 42 | Zyphra/ZONOS3-Mini FR | 12,980 | — | text-to-speech | ✓ |
| 43 | unsloth/LTX-2.5-GGUF FR | 11,247 | GGUF (inconnu) | image-to-video | ✓ |
| 44 | gradium/phonon-31m-en | 10,900 | 41.0MB | text-to-speech | |
| 45 | google/gemma-4-E2B-it FR | 10,442 | 5.1B | any-to-any | ✓ |
| 46 | Efficient-Large-Model/Open-H3-Regenerate-2K-IC | 9,870 | — | video-to-video | |
| 47 | Viggle/Viggle-Remake | 9,279 | — | video-to-video | |
| 48 | google/embeddinggemma-2 FR | 9,146 | 0.7B | feature-extraction | ✓ |
| 49 | inclusionAI/invoker-render-1.0 | 9,112 | 33.1B | video-to-video | |
| 50 | google/gemma-4-12B-it FR | 8,726 | 12.0B | any-to-any | ✓ |
| 51 | Winnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI | 8,508 | ≈20.1B | image-to-video | |
| 52 | Pika-Labs/Pika-H3-Flex-Turbo-LoRA | 8,214 | — | image-to-video | |
| 53 | pyannote/speaker-diarization-community-1 | 8,198 | — | automatic-speech-recognition | |
| 54 | lodestones/MOSS-Image-SFT-8-steps-dmd | 7,996 | 5.1B | other | |
| 55 | BennyDaBall/HyperFlow-H3-Flash-INT8-ComfyUI | 7,272 | ≈16.3B | image-text-to-video | |
| 56 | circlestone-labs/Anima | 7,042 | ≈2.1B | image-to-image | |
| 57 | google/gemma-4-12B-it-qat-q4_0-gguf FR | 6,989 | 12.0B (GGUF) | any-to-any | ✓ |
| 58 | microsoft/TRELLIS.2-4B FR | 6,921 | ≈1.3B | image-to-3d | ✓ |
| 59 | zai-org/GLM-OCR FR | 6,594 | 1.3B | image-to-text | ✓ |
| 60 | sakasegawa/Haru-4B-GGUF FR | 6,416 | 4.0B (GGUF) | audio-to-audio | ✓ |
| 61 | litert-community/gemma-4-E2B-it-litert-lm FR | 6,345 | 2.0B | other | ✓ |
| 62 | openai/whisper-large-v3-turbo FR | 6,043 | 0.8B | automatic-speech-recognition | ✓ |
| 63 | google/gemma-4-E4B-it-qat-q4_0-gguf FR | 5,752 | 4.0B (GGUF) | any-to-any | ✓ |
| 64 | pyannote/speaker-diarization-3.1 | 5,616 | — | automatic-speech-recognition | |
| 65 | Qwen/Qwen3-ASR-1.7B FR | 5,362 | 2.3B | automatic-speech-recognition | ✓ |
| 66 | LiquidAI/d1-Omni-2B-GGUF FR | 5,311 | 2.0B (GGUF) | audio-text-to-text | ✓ |
| 67 | facebook/sam3 | 5,013 | 0.9B | mask-generation | |
| 68 | ResembleAI/chatterbox FR | 4,578 | ≈1.1B | text-to-speech | ✓ |
| 69 | google/timesfm-3.0-pytorch | 4,425 | 0.3B | time-series-forecasting | |
| 70 | pyannote/segmentation-3.0 | 3,932 | — | voice-activity-detection | |
| 71 | HAL-X-AI/THX-02 | 3,861 | 4.5B | zero-shot-classification | |
| 72 | nvidia/Kumo-Tabular | 3,747 | — | other | |
| 73 | Comfy-Org/PAN2 | 3,357 | ≈33.7B | text-to-video | |
| 74 | nvidia/Nemotron-3-Diarization | 3,004 | 99.0MB | voice-activity-detection | |
| 75 | openai/whisper-large-v3 FR | 2,978 | 1.5B | automatic-speech-recognition | ✓ |
| 76 | pfnet/plamo-3-translate-2b-GGUF FR | 2,971 | 2.0B (GGUF) | translation | ✓ |
| 77 | vllm-sr/d3-flash | 2,469 | 8.4B | zero-shot-classification | |
| 78 | drbaph/MiniMax-H3-Turbo-Lora-ComfyUI | 2,400 | — | text-to-video | |
| 79 | microsoft/VibeVoice-ASR FR | 2,377 | 8.7B | automatic-speech-recognition | ✓ |
| 80 | akatz-ai/MiniMax-H3-Character-Swap-LoRA | 2,356 | — | video-to-video | |
| 81 | google/embeddinggemma-300m FR | 1,980 | 0.3B | sentence-similarity | ✓ |
| 82 | larryvrh/MiniMax-H3-Turbo-Lora | 1,915 | — | text-to-video | |
| 83 | ZhengmingYu/DMAD | 1,901 | ≈1.0B | text-to-video | |
| 84 | unsloth/embeddinggemma-2-GGUF FR | 1,893 | GGUF (inconnu) | feature-extraction | ✓ |
| 85 | speridlabs/idol | 1,683 | ≈0.7B | image-to-3d | |
| 86 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,491 | 0.3B | image-feature-extraction | |
| 87 | fal/MiniMax-H3-Realism-People-LoRA | 1,317 | — | image-text-to-video | |
| 88 | ZhengPeng7/BiRefNet | 1,169 | 0.2B | image-segmentation | |
| 89 | lodestones/MOSS-Image-Base-8-steps-dmd | 1,041 | 5.1B | other | |
| 90 | nvidia/personaplex-7b-v1 | 990 | 8.4B | audio-to-audio | |
| 91 | higurashi-ai/Haru-4B FR | 915 | 5.3B | audio-to-audio | ✓ |
| 92 | mistralai/Timestral-209M | 828 | 0.2B | time-series-forecasting | |
| 93 | OpenMOSS-Team/MOSS-Transcribe-Diarize FR | 805 | 0.9B | audio-text-to-text | ✓ |
| 94 | Remtir/AksonOCR-Lite | 794 | — | image-to-text | |
| 95 | stabilityai/stable-audio-3-medium | 730 | 2.3B | text-to-audio | |
| 96 | facebook/dinov3-vitb16-pretrain-lvd1689m | 711 | 86.0MB | image-feature-extraction | |
| 97 | LiconStudio/Minimax-H3-VBVR | 649 | ≈75.0MB | other | |
| 98 | facebook/sam3.1 | 605 | — | mask-generation | |
| 99 | tencent/Hunyuan3D-2 | 548 | ≈2.5B | image-to-3d | |
| 100 | pablodawson/MiniMax-H3-360-Orbit-LoRA | 533 | — | image-text-to-video | |
| 101 | pixai-labs/pixai-tagger-v1.0 | 530 | 0.5B | image-classification | |
| 102 | openai/privacy-filter | 526 | 1.4B | token-classification | |
| 103 | briaai/RMBG-2.0 | 521 | 0.2B | image-segmentation | |
| 104 | vllm-sr/d3-mini | 520 | 4.5B | zero-shot-classification | |
| 105 | nvidia/NVIDIA-NemotronLabs-RE-USE | 458 | 10.0MB | audio-to-audio | |
| 106 | stabilityai/stable-audio-3-small-sfx | 427 | 0.6B | text-to-audio | |
| 107 | baselabs/mammoth-1 | 400 | 27.4B | text-classification | |
| 108 | meituan-longcat/LongCat-Video-Avatar-1.6 | 367 | ≈2.7B | other | |
| 109 | facebook/dinov3-vits16-pretrain-lvd1689m | 355 | 22.0MB | image-feature-extraction | |
| 110 | ACE-Step/Ace-Step1.5 | 351 | ≈1.5B | text-to-audio | |
| 111 | Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details | 346 | 22.0B | video-to-video | |
| 112 | ggml-org/Laya-GGUF | 330 | GGUF (inconnu) | text-classification | |
| 113 | baselabs/elephant-1 | 313 | 9.4B | text-classification | |
| 114 | nvidia/Nemotron-3.5-Embed-8B-BF16 FR | 305 | 8.4B | visual-document-retrieval | ✓ |
| 115 | Lightricks/LTX-2.5-Diffusers FR | 296 | 19.0B | text-to-video | ✓ |
| 116 | ContinuousIntelligence/ci-proto | 291 | — | time-series-forecasting | |
| 117 | ai-coustics/vad-voice-focus | 290 | — | voice-activity-detection | |
| 118 | m-a-p/YuE2-3B | 282 | 3.6B | text-to-audio | |
| 119 | kobimusic/dettato | 268 | 15.0MB | other | |
| 120 | Prior-Labs/tabpfn_3_5 | 261 | ≈0.4B | tabular-classification | |
| 121 | convaiinnovations/laya | 250 | 0.4B | text-classification | |
| 122 | lerobot/smolvla_base | 245 | 0.5B | robotics | |
| 123 | LiquidAI/d1-Omni-2B FR | 242 | 2.2B | audio-text-to-text | ✓ |
| 124 | elix3r/gemma4-12b-with-proj-ltx-2.5-GGUF FR | 236 | 12.0B (GGUF) | feature-extraction | ✓ |
| 125 | tencent/Hunyuan3D-2.1 | 231 | ≈0.6B | image-to-3d | |
| 126 | rayline-ai/ARC-1.0 | 220 | 0.6B | text-classification | |
| 127 | hyz317/HairDeck | 213 | ≈0.4B | image-to-3d | |
| 128 | perplexity-ai/pplx-decider-flash-v1.3 | 194 | 4.5B | text-classification | |
| 129 | prithivMLmods/VibeVoice-ASR-HF-GGUF FR | 194 | GGUF (inconnu) | audio-text-to-text | ✓ |
| 130 | ai-coustics/tyto | 168 | — | other | |
| 131 | briaai/RMBG-3.0-Comfy | 161 | ≈8.2B | image-segmentation | |
| 132 | jgkwak/solv3r | 154 | ≈0.2B | image-to-3d | |
| 133 | stabilityai/stable-audio-3-small-music | 152 | 0.6B | text-to-audio | |
| 134 | datalab-to/indra-ocr FR | 152 | 1.0MB | image-to-text | ✓ |
| 135 | LiquidAI/Liquid-Codec FR | 146 | 74.0MB | feature-extraction | ✓ |
| 136 | vllm-sr/d3-ultra | 125 | 26.1B | zero-shot-classification | |
| 137 | facebook/dinov3-vith16plus-pretrain-lvd1689m | 123 | 0.8B | image-feature-extraction | |
| 138 | minishlab/blink-8M | 118 | 8.0MB | feature-extraction | |
| 139 | vllm-sr/d3-turbo | 114 | 26.1B | zero-shot-classification | |
| 140 | tencent/Hy-MT2-1.8B FR | 111 | 2.0B | translation | ✓ |
| 141 | tencent/HunyuanVideo | 105 | — | text-to-video | |
| 142 | neuphonic/neucodec | 104 | 0.6B | audio-to-audio | |
| 143 | iapp/OpenThai2.1-OCR-Text-20261118 | 98 | — | image-to-text | |
| 144 | Ultralytics/YOLO26 FR | 93 | — | object-detection | ✓ |
| 145 | openjev/openjev FR | 83 | 27.4B | zero-shot-classification | ✓ |
| 146 | tomaarsen/TinyCLIP-39M-PixelArt | 78 | 83.0MB | sentence-similarity | |
| 147 | MiniMaxAI/MiniMax-Music3 | 50 | 2.4B | text-to-audio | |
| 148 | apple/DepthPro2-focal | 42 | 23.0MB | depth-estimation | |
| 149 | kkt94/Llama-V-JEPA-LM-Qwen3-30B-A3B FR | 41 | 32.4B / 3.0B MOE | video-text-to-text | ✓ |
| 150 | nvidia/Alpamayo2-Edge | 36 | 2.7B | robotics | |
| 151 | ai-coustics/vad-multi-speaker | 35 | — | voice-activity-detection | |
| 152 | charcot-ai/marimba | 34 | ≈52.0MB | audio-classification | |
| 153 | FrontiersMind/NandiBERT-150M FR | 28 | 0.2B | fill-mask | ✓ |
| 154 | opensearch-project/opensearch-neural-embed-v1 | 27 | 0.6B | sentence-similarity | |
| 155 | FrontiersMind/NandiBERT-450M FR | 24 | 0.5B | fill-mask | ✓ |
| 156 | f4roukb/denserepr-code-48M-pretrain-EN-v1 | 20 | 48.0MB | sentence-similarity | |
| 157 | racineai/Jevol-0.6B | 17 | 0.6B | robotics | |
| 158 | racineai/Jevol-0.9B | 17 | 0.9B | robotics | |
| 159 | racineai/Jevol-2B | 16 | 2.2B | robotics | |
| 160 | Roboflow/rf-detr-large | 15 | 34.0MB | object-detection | |
| 161 | briaai/RMBG-3.0 | 15 | 8.1B | image-segmentation | |
| 162 | facebook/dinov3-vit7b16-pretrain-lvd1689m | 15 | 6.7B | image-feature-extraction | |
| 163 | gertelrina/aadd | 13 | — | audio-classification | |
| 164 | desert-ant-labs/ear FR | 8 | — | audio-classification | ✓ |
| 165 | apple/DepthPro2-H | 6 | 0.9B | depth-estimation | |
| 166 | apple/DepthPro2-S | 5 | 24.0MB | depth-estimation | |
| 167 | apple/DepthPro2-L | 5 | 0.3B | depth-estimation | |
| 168 | nvidia/nemotron-labs-audio-visual-flamingo-hf | 3 | 8.7B | video-text-to-text | |
| 169 | anon-review-meld-2026/meld | 3 | 1.0B | fill-mask | |
| 170 | tencent/HY-Motion-1.0 | 1 | — | text-to-3d | |
| 171 | tencent/WeVisForensics | 0 | — | video-text-to-text | |
| 172 | apple/DepthPro2 | 0 | — | depth-estimation | |
| 173 | speridlabs/iris-z | 0 | ≈2.5B | depth-estimation | |
| 174 | inworld/sava | 0 | ≈26.0MB | voice-activity-detection | |
| 175 | bageldotcom/Bagel-Robotics-1 | 0 | — | robotics | |
| 176 | iapp/OpenThai2.0-LATTE-WordSeg-Lite | 0 | — | token-classification | |