249 modèles dans 43 catégories | Généré le 06/10/2026 22:33 UTC
249 modèles sélectionnés
| # | Modele | DL/Jour | Params | pipeline | FR |
|---|---|---|---|---|---|
| 1 | Comfy-Org/MiniMax-H3 | 349,489 | — | image-to-image | — |
| 2 | Comfy-Org/Qwen-Image-2.1 FR | 328,565 | — | image-to-image | ✓ |
| 3 | autotrust/JEV-27B-VL | 254,214 | 27.8B | image-text-to-text | — |
| 4 | prism-ml/Ternary-Bonsai-2-27B-gguf | 220,728 | 27.0B (GGUF) | text-generation | — |
| 5 | autotrust/GEV-26B-Decide | 213,644 | 25.8B | text-classification | — |
| 6 | zai-org/GLM-5.3-Flash FR | 141,723 | 321.3B | image-text-to-text | ✓ |
| 7 | sentence-transformers/all-MiniLM-L6-v2 | 140,328 | 23.0MB | sentence-similarity | — |
| 8 | unsloth/Qwen3.8-27B-GGUF FR | 121,608 | 27.0B (GGUF) | conversational | ✓ |
| 9 | Qwen/Qwen3.8-27B FR | 109,162 | 27.8B | image-text-to-text | ✓ |
| 10 | abenzerps/Qwen-Image-2.1-Uncensored-GGUF FR | 107,610 | GGUF (inconnu) | text-to-image | ✓ |
| 11 | ornith-ai/Ornith-1.5-9B-GGUF | 104,432 | 9.0B (GGUF) | text-generation | — |
| 12 | mudler/locate-anything.cpp-gguf | 93,562 | GGUF (inconnu) | object-detection | — |
| 13 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR | 93,441 | GGUF (inconnu) | image-text-to-text | ✓ |
| 14 | SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR | 92,307 | GGUF (inconnu) | image-text-to-text | ✓ |
| 15 | Qwen/Qwen3.8-27B-FP8 FR | 88,777 | 27.8B | image-text-to-text | ✓ |
| 16 | Comfy-Org/Krea-2 | 74,487 | — | image-to-image | — |
| 17 | ornith-ai/Ornith-1.5-35B-A3B-GGUF | 72,942 | 35.0B (GGUF) (MOE) MOE | text-generation | — |
| 18 | audio-cpp/audio.cpp-gguf | 72,198 | GGUF (inconnu) | text-to-speech | — |
| 19 | deepseek-ai/DeepSeek-V4-Flash-0731 FR | 67,796 | 304.2B | text-generation | ✓ |
| 20 | amazon/chronos-2 | 64,204 | 0.1B | time-series-forecasting | — |
| 21 | DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF FR | 60,737 | 27.0B (GGUF) | image-text-to-text | ✓ |
| 22 | google/gemma-4-26B-A4B-it FR | 60,445 | 25.8B / 4.0B MOE | image-text-to-text | ✓ |
| 23 | Qwen/Qwen3-0.6B FR | 58,435 | 0.8B | text-generation | ✓ |
| 24 | cross-encoder/ms-marco-MiniLM-L6-v2 | 49,966 | 23.0MB | text-ranking | — |
| 25 | MiniMaxAI/MiniMax-H3 | 49,783 | 33.1B | image-text-to-video | — |
| 26 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF FR | 47,863 | GGUF (inconnu) | image-text-to-text | ✓ |
| 27 | google/gemma-4-31B-it FR | 46,025 | 31.3B | image-text-to-text | ✓ |
| 28 | unsloth/Qwen-Image-2.1-GGUF FR | 45,567 | GGUF (inconnu) | text-to-image | ✓ |
| 29 | nvidia/Qwen3.6-35B-A3B-NVFP4 FR | 43,434 | 18.7B / 3.0B MOE | text-generation | ✓ |
| 30 | JonathanColetti/Qwen3.8-27B-Uncensored-GGUF FR | 42,486 | 27.0B (GGUF) | text-generation | ✓ |
| 31 | unsloth/Qwen3.8-27B-NVFP4 FR | 41,977 | 19.9B | other | ✓ |
| 32 | ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF FR | 41,901 | 27.0B (GGUF) | text-generation | ✓ |
| 33 | openbmb/MiniCPM5-2B | 39,742 | 2.5B | text-generation | — |
| 34 | zai-org/GLM-5.3 FR | 35,456 | 753.3B | text-generation | ✓ |
| 35 | BAAI/bge-m3 FR | 34,608 | — | sentence-similarity | ✓ |
| 36 | google/timesfm-3.0-pytorch | 31,814 | 0.3B | time-series-forecasting | — |
| 37 | Comfy-Org/z_image_turbo | 27,575 | — | image-to-image | — |
| 38 | unsloth/MiniMax-H3-GGUF | 27,212 | GGUF (inconnu) | image-text-to-video | — |
| 39 | mradermacher/Ornith-1.5-9B-uncensored-GGUF | 26,122 | 9.0B (GGUF) | conversational | — |
| 40 | lightx2v/Minimax-h3-Turbo | 25,328 | — | image-to-video | — |
| 41 | autotrust/JEV-9B | 24,104 | 9.0B | text-classification | — |
| 42 | google-bert/bert-base-uncased | 23,162 | 0.1B | fill-mask | — |
| 43 | Lightricks/LTX-2.5 FR | 22,387 | — | image-to-video | ✓ |
| 44 | MATLOWAI/minimax-h3-fused-turbo-int8-convrot | 21,888 | — | image-text-to-video | — |
| 45 | Viggle/Qwen-Image-2.1-viggle-turbo FR | 21,602 | 7.1B | text-to-image | ✓ |
| 46 | google/gemma-4-E4B-it FR | 20,384 | 8.0B | any-to-any | ✓ |
| 47 | Qwen/Qwen3-Embedding-0.6B FR | 18,886 | 0.6B | feature-extraction | ✓ |
| 48 | WarmBloodAban/Minimax-h3_Singularity | 18,476 | — | image-to-video | — |
| 49 | PrunaAI/Pruna-Qwen-Image-2.1 FR | 17,999 | — | text-to-image | ✓ |
| 50 | hexgrad/Kokoro-82M | 17,281 | — | text-to-speech | — |
| 51 | Mapika/decider-2b | 15,773 | 1.9B | text-classification | — |
| 52 | mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF | 15,487 | 9.0B (GGUF) | conversational | — |
| 53 | autotrust/JEV-27B | 15,280 | 26.9B | text-classification | — |
| 54 | Comfy-Org/Wan_2.2_ComfyUI_Repackaged | 15,116 | — | image-to-video | — |
| 55 | google-t5/t5-small FR | 14,683 | 61.0MB | translation | ✓ |
| 56 | google/gemma-4-E2B-it FR | 13,887 | 5.1B | any-to-any | ✓ |
| 57 | google/gemma-4-12B-it FR | 13,098 | 12.0B | any-to-any | ✓ |
| 58 | pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF | 13,081 | GGUF (inconnu) | image-to-image | — |
| 59 | FastVideo/FastVideo-FastH3-Comfy | 12,844 | — | image-to-image | — |
| 60 | openai/clip-vit-base-patch32 | 12,240 | — | zero-shot-image-classification | — |
| 61 | Comfy-Org/YuE2 | 11,004 | — | image-to-image | — |
| 62 | Comfy-Org/Ming-Image | 10,738 | — | image-to-image | — |
| 63 | pyannote/speaker-diarization-community-1 | 10,249 | — | automatic-speech-recognition | — |
| 64 | intfloat/multilingual-e5-small FR | 9,415 | 0.1B | sentence-similarity | ✓ |
| 65 | autotrust/GEV-26B-Decide-NVFP4 | 9,282 | 14.4B | text-classification | — |
| 66 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice FR | 9,098 | 1.9B | text-to-speech | ✓ |
| 67 | nvidia/Cosmos3-Edge | 8,996 | 3.9B | other | — |
| 68 | nvidia/nemotron-3.5-asr-streaming-0.6b FR | 8,906 | 0.6B | automatic-speech-recognition | ✓ |
| 69 | openai/whisper-large-v3-turbo FR | 8,597 | 0.8B | automatic-speech-recognition | ✓ |
| 70 | google/embeddinggemma-300m FR | 8,090 | 0.3B | sentence-similarity | ✓ |
| 71 | Bingsu/adetailer | 7,708 | — | other | — |
| 72 | fidel1234/Krea2_Asian_Character | 7,627 | — | image-to-image | — |
| 73 | k2-fsa/OmniVoice FR | 7,626 | 0.6B | text-to-speech | ✓ |
| 74 | ornith-ai/Ornith-1.5-35B-A3B-DFlash | 7,450 | 0.4B / 3.0B MOE | other | — |
| 75 | mistralai/Voxtral-Mini-4B-Realtime-2602 FR | 7,432 | 4.4B | automatic-speech-recognition | ✓ |
| 76 | zai-org/GLM-OCR FR | 7,428 | 1.3B | image-to-text | ✓ |
| 77 | litert-community/gemma-4-E2B-it-litert-lm FR | 7,237 | 2.0B | other | ✓ |
| 78 | Comfy-Org/Pixal3D | 6,911 | — | image-to-image | — |
| 79 | pyannote/speaker-diarization-3.1 | 6,718 | — | automatic-speech-recognition | — |
| 80 | unsloth/Qwen-Image-2.1-FP8 FR | 6,638 | — | text-to-image | ✓ |
| 81 | audio-cpp/Yue2-3B-GGUF | 6,585 | 3.0B (GGUF) | text-to-audio | — |
| 82 | facebook/sam3 | 6,545 | 0.9B | mask-generation | — |
| 83 | google/gemma-4-12B-it-qat-q4_0-gguf FR | 6,410 | 12.0B (GGUF) | any-to-any | ✓ |
| 84 | answerdotai/ModernBERT-base | 6,308 | 0.1B | fill-mask | — |
| 85 | google/vit-base-patch16-224 | 6,250 | 87.0MB | image-classification | — |
| 86 | coqui/XTTS-v2 | 6,233 | — | text-to-speech | — |
| 87 | Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1 FR | 6,206 | — | text-to-image | ✓ |
| 88 | microsoft/TRELLIS.2-4B FR | 6,110 | 4.0B | image-to-3d | ✓ |
| 89 | Qwen/Qwen3-ASR-1.7B FR | 5,544 | 2.3B | automatic-speech-recognition | ✓ |
| 90 | Abiray/Qwen-Image-2.1-GGUF FR | 5,376 | GGUF (inconnu) | text-to-image | ✓ |
| 91 | wfzyx/von | 5,336 | 0.4B | zero-shot-classification | — |
| 92 | fastino/GLiNER2.5-Decide | 5,264 | 0.5B | token-classification | — |
| 93 | fastino/gliner2.5-multi-v1 FR | 5,168 | 0.3B | token-classification | ✓ |
| 94 | ornith-ai/Ornith-1.5-9B-DFlash | 5,072 | 1.3B | other | — |
| 95 | Lightricks/LTX-2.3 FR | 4,883 | — | image-to-video | ✓ |
| 96 | pyannote/segmentation-3.0 | 4,823 | — | voice-activity-detection | — |
| 97 | Qwen/Qwen-Image-2.1 FR | 4,660 | 7.1B | text-to-image | ✓ |
| 98 | unsloth/gemma-4-12B-it-qat-GGUF FR | 4,435 | 12.0B (GGUF) | any-to-any | ✓ |
| 99 | Winnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI | 4,378 | — | image-to-video | — |
| 100 | Qwen/Qwen3-VL-Embedding-2B FR | 4,242 | 2.1B | sentence-similarity | ✓ |
| 101 | pottokao/Qwen-Image-2.1-PE-I2I-Heretic-GGUF FR | 4,098 | GGUF (inconnu) | conversational | ✓ |
| 102 | openai/whisper-large-v3 FR | 3,803 | 1.5B | automatic-speech-recognition | ✓ |
| 103 | stabilityai/stable-diffusion-xl-base-1.0 | 3,734 | 2.6B | text-to-image | — |
| 104 | QuantFunc/Minimax-H3-Quantfunc-4bit | 3,686 | 4.0B | text-to-video | — |
| 105 | unsloth/gemma-4-E4B-it-qat-GGUF FR | 3,469 | 4.0B (GGUF) | any-to-any | ✓ |
| 106 | Qwen/Qwen3-ASR-1.7B-hf FR | 3,386 | 2.0B | automatic-speech-recognition | ✓ |
| 107 | larryvrh/MiniMax-H3-Turbo-Lora | 3,378 | — | text-to-video | — |
| 108 | mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-GGUF FR | 3,305 | GGUF (inconnu) | conversational | ✓ |
| 109 | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive FR | 3,291 | 9.0B | conversational | ✓ |
| 110 | drbaph/MiniMax-H3-Turbo-Lora-ComfyUI | 3,263 | — | text-to-video | — |
| 111 | ggml-org/Bespoke-Nimble-9B-v3-GGUF | 3,142 | 9.0B (GGUF) | zero-shot-classification | — |
| 112 | ResembleAI/chatterbox FR | 3,097 | — | text-to-speech | ✓ |
| 113 | nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF FR | 2,963 | 27.0B (GGUF) | conversational | ✓ |
| 114 | openbmb/VoxCPM2 FR | 2,853 | 2.3B | text-to-speech | ✓ |
| 115 | google/gemma-4-E4B FR | 2,748 | 8.0B | any-to-any | ✓ |
| 116 | KasugaiSakura/Qwen-Image-2.1-Uncensored-Abenzerps-GGUF FR | 2,706 | GGUF (inconnu) | text-to-image | ✓ |
| 117 | Edge0/Audio8-ASR-Infinite | 2,693 | 4.1B | automatic-speech-recognition | — |
| 118 | google/gemma-4-E2B-it-qat-q4_0-gguf FR | 2,629 | 2.0B (GGUF) | any-to-any | ✓ |
| 119 | mistralai/Mistral-7B-Instruct-v0.3 | 2,463 | 7.2B | other | — |
| 120 | Qwen/Qwen3-TTS-12Hz-0.6B-Base FR | 2,292 | 0.9B | text-to-speech | ✓ |
| 121 | openai/whisper-small FR | 2,200 | 0.2B | automatic-speech-recognition | ✓ |
| 122 | openai/privacy-filter | 2,039 | 1.4B | token-classification | — |
| 123 | akatz-ai/MiniMax-H3-Character-Swap-LoRA | 1,850 | — | video-to-video | — |
| 124 | speach1sdef178/MiniMax-H3-X2-Detail-VAE | 1,834 | — | image-to-video | — |
| 125 | bartowski/TheDrummer_Artemis-31B-v1.2-GGUF | 1,750 | 31.0B (GGUF) | any-to-any | — |
| 126 | Mapika/decider-4b | 1,729 | 4.2B | text-classification | — |
| 127 | nvidia/Nemotron-3-Diarization | 1,677 | 99.0MB | voice-activity-detection | — |
| 128 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,640 | 0.3B | image-feature-extraction | — |
| 129 | OpenMOSS-Team/MOSS-Transcribe-Diarize FR | 1,568 | 0.9B | audio-text-to-text | ✓ |
| 130 | ggml-org/Laya-GGUF | 1,531 | GGUF (inconnu) | text-classification | — |
| 131 | turboderp/Qwen3.8-27B-exl3 FR | 1,475 | 27.0B | other | ✓ |
| 132 | alibaba-pai/MiniMax-H3-Acc-LoRAs | 1,381 | — | text-to-video | — |
| 133 | fal/MiniMax-H3-Realism-People-LoRA | 1,380 | — | image-text-to-video | — |
| 134 | fastino/gliner2-privacy-filter-PII-multi FR | 1,339 | 0.3B | token-classification | ✓ |
| 135 | madebyollin/texture-fix-vae-for-qwen-image-2.1 FR | 1,298 | 0.3B | other | ✓ |
| 136 | m-a-p/YuE2-3B | 1,293 | 3.6B | text-to-audio | — |
| 137 | facebook/dinov3-vitb16-pretrain-lvd1689m | 1,213 | 86.0MB | image-feature-extraction | — |
| 138 | dealignai/GLM-5.3-Flash-UNCENSORED-FP8 | 1,211 | 321.3B | other | — |
| 139 | IndexTeam/Index-Translate-9B-GGUF | 1,134 | 9.0B (GGUF) | translation | — |
| 140 | convaiinnovations/laya | 1,133 | 0.4B | text-classification | — |
| 141 | drbaph/Hyperflow-Comfyui | 1,130 | — | image-text-to-video | — |
| 142 | alibaba-pai/MiniMax-H3-Fun-Controlnet-Union-2.0 | 1,123 | — | text-to-video | — |
| 143 | SulphurAI/Sulphur-2-base | 1,105 | — | text-to-video | — |
| 144 | jaredpalmer/kev-4b | 1,067 | 4.0B | text-classification | — |
| 145 | google/gemma-4-E2B FR | 1,045 | 5.1B | any-to-any | ✓ |
| 146 | fastino/GLiNER2.5-multi-Decide FR | 1,037 | 0.3B | token-classification | ✓ |
| 147 | autotrust/JEV-Gemma4-26B-A4B FR | 1,036 | 25.8B / 4.0B MOE | text-classification | ✓ |
| 148 | pablodawson/MiniMax-H3-360-Orbit-LoRA | 972 | — | image-text-to-video | — |
| 149 | QuantStack/Wan2.2-I2V-A14B-GGUF | 955 | 14.0B (GGUF) | image-to-video | — |
| 150 | ZhengPeng7/BiRefNet | 933 | 0.2B | image-segmentation | — |
| 151 | m-a-p/SheetSage2 | 902 | 57.0MB | feature-extraction | — |
| 152 | HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive FR | 892 | 4.0B | conversational | ✓ |
| 153 | bosonai/higgs-tts-3-4b FR | 866 | 4.7B | text-to-speech | ✓ |
| 154 | IndexTeam/Index-Translate-2B-GGUF | 851 | 2.0B (GGUF) | translation | — |
| 155 | facebook/bart-large-cnn | 832 | 0.4B | summarization | — |
| 156 | ChrisColeTech/LTX-2.3-uncensored-v1.4-FP8 | 822 | — | text-to-video | — |
| 157 | samuel-vitorino/sopro-v2-turbo FR | 732 | 0.1B | text-to-speech | ✓ |
| 158 | Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details | 710 | 22.0B | video-to-video | — |
| 159 | pixai-labs/pixai-tagger-v1.0 | 695 | 0.5B | image-classification | — |
| 160 | manjunathshiva/opendecider-nano | 685 | 0.4B | zero-shot-classification | — |
| 161 | nvidia/GR00T-N1.7-3B | 669 | 3.1B | robotics | — |
| 162 | iapp/OpenThai-SystemOne | 658 | 0.8B | zero-shot-classification | — |
| 163 | facebook/dinov3-vits16-pretrain-lvd1689m | 632 | 22.0MB | image-feature-extraction | — |
| 164 | briaai/RMBG-2.0 | 623 | 0.2B | image-segmentation | — |
| 165 | nvidia/personaplex-7b-v1 | 622 | 8.4B | audio-to-audio | — |
| 166 | openjev/openjev-GGUF | 607 | GGUF (inconnu) | conversational | — |
| 167 | szwagros/SoL-Refiner-LTX-2.5-H3-int8-convrot | 602 | — | video-to-video | — |
| 168 | realrebelai/LTX-2.5_GGUFs | 592 | GGUF (inconnu) | text-to-video | — |
| 169 | mlx-community/clef-flash-4bit | 557 | 9.4B | zero-shot-classification | — |
| 170 | brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final-GGUF | 550 | GGUF (inconnu) | conversational | — |
| 171 | Viggle/Viggle-Animate | 543 | 33.1B | video-to-video | — |
| 172 | facebook/nllb-200-distilled-600M FR | 526 | — | translation | ✓ |
| 173 | Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen | 512 | 22.0B | video-to-video | — |
| 174 | IndexTeam/Index-Translate-35B-A3B-preview-GGUF | 492 | 35.0B (GGUF) (MOE) MOE | translation | — |
| 175 | ggml-org/lev-GGUF | 484 | GGUF (inconnu) | zero-shot-classification | — |
| 176 | Jojocodex/wushu-action-v7-minimax-h3-fl2va-ref2va-lora | 472 | — | image-to-video | — |
| 177 | Iwannapose/minimax_h3_pdmd_4nfe_comfyui | 461 | — | text-to-video | — |
| 178 | czl/CLM-v0.1-8B-GGUF | 432 | 8.0B (GGUF) | text-ranking | — |
| 179 | stabilityai/stable-audio-3-medium | 432 | 2.3B | text-to-audio | — |
| 180 | Lightricks/LTX-2.5-22b-IC-LoRA-SDR-To-HDR | 421 | 22.0B | video-to-video | — |
| 181 | Prior-Labs/tabpfn_3_5 | 378 | — | tabular-classification | — |
| 182 | pdmd2026/pdmd_4NFE_lora | 358 | — | text-to-video | — |
| 183 | openjev/openjev FR | 346 | 27.4B | zero-shot-classification | ✓ |
| 184 | Lightricks/LTX-2.5-22b-IC-LoRA-Restore | 296 | 22.0B | video-to-video | — |
| 185 | jeff-legacy/Jeff-Qwen3.5-0.8B FR | 283 | 0.9B | zero-shot-classification | ✓ |
| 186 | hoidhxd/MiniMax-H3-x-Z-Image-hybrid | 281 | — | image-to-video | — |
| 187 | briaai/RMBG-1.4 | 275 | 44.0MB | image-segmentation | — |
| 188 | Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients | 267 | 22.0B | video-to-video | — |
| 189 | facebook/sam3.1 | 264 | — | mask-generation | — |
| 190 | Contrastive-LM/CLM-v0.1-8B | 260 | 8.0B | text-ranking | — |
| 191 | ACE-Step/Ace-Step1.5 | 259 | — | text-to-audio | — |
| 192 | PSRben/VisionHOPE | 250 | — | image-classification | — |
| 193 | stabilityai/stable-audio-3-small-sfx | 244 | 0.6B | text-to-audio | — |
| 194 | jhu-clsp/mmBERT-small | 225 | — | fill-mask | — |
| 195 | Qwen/Qwen-Image-Layered FR | 217 | 20.4B | image-text-to-image | ✓ |
| 196 | tencent/Hy-MT2-1.8B FR | 215 | 2.0B | translation | ✓ |
| 197 | mlx-community/clef-4bit | 198 | 27.4B | zero-shot-classification | — |
| 198 | numind/NuExtract3 FR | 197 | 4.5B | image-to-text | ✓ |
| 199 | mlx-community/clef-8bit | 192 | 27.4B | zero-shot-classification | — |
| 200 | Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render | 187 | 22.0B | video-to-video | — |
| 201 | topk-io/topk-embed-v1-small FR | 171 | 2.2B | feature-extraction | ✓ |
| 202 | fastino/GLiNER2.5-Decide-1B | 170 | 1.2B | token-classification | — |
| 203 | Abiray/10Eros-Max-Turbo-Hybrid-Beta5-GGUF | 150 | GGUF (inconnu) | image-text-to-video | — |
| 204 | Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler | 148 | 22.0B | video-to-video | — |
| 205 | tencent/Hunyuan3D-2.1 | 123 | — | image-to-3d | — |
| 206 | vllm-sr/Decision-2.0-Kai-0.6B | 119 | 0.6B | feature-extraction | — |
| 207 | MiniMaxAI/MiniMax-Music3 | 117 | 2.4B | text-to-audio | — |
| 208 | MahmoodLab/UNI2-h | 107 | — | image-feature-extraction | — |
| 209 | IndexTeam/Index-Translate-9B | 106 | 9.7B | translation | — |
| 210 | vllm-sr/Decision-2.0-Nox-4B | 99 | 4.0B | feature-extraction | — |
| 211 | topk-io/topk-embed-v1-xsmall FR | 99 | 0.9B | feature-extraction | ✓ |
| 212 | IndexTeam/Index-Translate-2B | 88 | 2.3B | translation | — |
| 213 | black-forest-labs/flux-3-action-so101 FR | 87 | 6.9B | robotics | ✓ |
| 214 | Ultralytics/YOLO26 FR | 75 | — | object-detection | ✓ |
| 215 | vllm-sr/Decision-2.0-Sol-2B | 74 | 2.0B | feature-extraction | — |
| 216 | black-forest-labs/flux-3-action-droid FR | 74 | 6.9B | robotics | ✓ |
| 217 | vllm-sr/Decision-2.0-Lux-9B | 69 | 9.0B | feature-extraction | — |
| 218 | vllm-sr/Decision-2.0-Eos-0.8B | 67 | 0.8B | feature-extraction | — |
| 219 | vllm-sr/Decision-2.0-Vega-27B | 65 | 27.0B | feature-extraction | — |
| 220 | MahmoodLab/UNI | 62 | — | image-feature-extraction | — |
| 221 | nvidia/RE-USE | 47 | 10.0MB | audio-to-audio | — |
| 222 | perplexity-ai/PII-Tracer FR | 45 | 0.6B | token-classification | ✓ |
| 223 | birlaailabs/yug | 33 | 0.3B | time-series-forecasting | — |
| 224 | nlpai-lab/RenderRank-2B | 30 | 2.1B | text-ranking | — |
| 225 | IndexTeam/Index-Nailong-9B | 30 | 9.0B | translation | — |
| 226 | black-forest-labs/flux-3-action-base FR | 28 | — | robotics | ✓ |
| 227 | stabilityai/stable-fast-3d | 25 | 1.0B | image-to-3d | — |
| 228 | bodhan-ai/indic-ocr | 24 | — | image-to-text | — |
| 229 | stabilityai/stable-audio-open-1.0 | 22 | 1.2B | text-to-audio | — |
| 230 | DecisionIntelligence/Aurora | 17 | 0.2B | time-series-forecasting | — |
| 231 | interfaze-ai/interfaze-1-lite FR | 13 | — | image-text-to-image | ✓ |
| 232 | MCG-NJU/OneStreamer-4B | 13 | 4.4B | video-text-to-text | — |
| 233 | desert-ant-labs/clear | 13 | — | audio-to-audio | — |
| 234 | KBlueLeaf/TTVidT | 12 | 0.2B | video-classification | — |
| 235 | LiquidAI/LFM2.5-Encoder-350M-GGUF FR | 8 | GGUF (inconnu) | fill-mask | ✓ |
| 236 | nlpai-lab/KURE-Reranker-nano | 7 | 0.1B | text-ranking | — |
| 237 | nums-ai/ephris | 5 | — | graph-ml | — |
| 238 | LiquidAI/LFM2.5-Encoder-230M-GGUF FR | 5 | GGUF (inconnu) | fill-mask | ✓ |
| 239 | nvidia/Lyra-2.0 | 4 | — | image-to-3d | — |
| 240 | StanfordAIMI/stanford-deidentifier-with-radiology-reports-and-i2b2 | 2 | 2.0B | token-classification | — |
| 241 | Falconsai/medical_summarization | 2 | 61.0MB | summarization | — |
| 242 | MeteoSwiss/Varda-single-1.0 | 0 | — | graph-ml | — |
| 243 | NU-World-Model-Embodied-AI/phyjudge-9B | 0 | 9.0B | video-text-to-text | — |
| 244 | nvidia/PixelUMM | 0 | — | image-to-text | — |
| 245 | inclusionAI/Ming-Image-0.1-Design-Layer | 0 | 6.2B | image-text-to-image | — |
| 246 | TencentARC/Pixal3D | 0 | — | image-to-3d | — |
| 247 | becausereasons/yue2-grvl-raspy-rock-soul | 0 | — | text-to-audio | — |
| 248 | marcelosantoskuw/paper_015153151_visual_question_answering | 0 | — | visual-question-answering | — |
| 249 | huawei-bayerlab/marigold-v2-0 | 0 | — | depth-estimation | — |