236 modèles dans 42 catégories | Généré le 09/10/2026 22:33 UTC
236 modèles sélectionnés
| # | Modele | DL/Jour | Params | pipeline | FR |
|---|---|---|---|---|---|
| 1 | Comfy-Org/MiniMax-H3 | 329,617 | — | image-to-image | — |
| 2 | Comfy-Org/Qwen-Image-2.1 FR | 323,146 | — | image-to-image | ✓ |
| 3 | prism-ml/Ternary-Bonsai-2-27B-gguf | 199,503 | 27.0B (GGUF) | text-generation | — |
| 4 | autotrust/JEV-27B-VL | 170,726 | 27.8B | image-text-to-text | — |
| 5 | zai-org/GLM-5.3-Flash FR | 142,022 | 321.3B | image-text-to-text | ✓ |
| 6 | sentence-transformers/all-MiniLM-L6-v2 | 135,638 | 23.0MB | sentence-similarity | — |
| 7 | autotrust/GEV-26B-Decide | 129,965 | 25.8B | text-classification | — |
| 8 | unsloth/Qwen3.8-27B-GGUF FR | 113,207 | 27.0B (GGUF) | conversational | ✓ |
| 9 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR | 111,229 | GGUF (inconnu) | image-text-to-text | ✓ |
| 10 | abenzerps/Qwen-Image-2.1-Uncensored-GGUF FR | 105,961 | GGUF (inconnu) | text-to-image | ✓ |
| 11 | Qwen/Qwen3.8-27B FR | 104,363 | 27.8B | image-text-to-text | ✓ |
| 12 | ornith-ai/Ornith-1.5-9B-GGUF | 102,866 | 9.0B (GGUF) | text-generation | — |
| 13 | mudler/locate-anything.cpp-gguf | 102,745 | GGUF (inconnu) | object-detection | — |
| 14 | SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR | 97,784 | GGUF (inconnu) | image-text-to-text | ✓ |
| 15 | Qwen/Qwen3.8-27B-FP8 FR | 79,669 | 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 | 72,053 | 35.0B (GGUF) (MOE) MOE | text-generation | — |
| 18 | deepseek-ai/DeepSeek-V4-Flash-0731 FR | 64,626 | 304.2B | text-generation | ✓ |
| 19 | Comfy-Org/Krea-2 | 61,229 | — | image-to-image | — |
| 20 | amazon/chronos-2 | 61,205 | 0.1B | time-series-forecasting | — |
| 21 | Qwen/Qwen3-0.6B FR | 58,282 | 0.8B | text-generation | ✓ |
| 22 | google/gemma-4-26B-A4B-it FR | 56,888 | 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 | 52,637 | 27.0B (GGUF) | image-text-to-text | ✓ |
| 24 | MiniMaxAI/MiniMax-H3 | 48,354 | 33.1B | image-text-to-video | — |
| 25 | cross-encoder/ms-marco-MiniLM-L6-v2 | 48,196 | 23.0MB | text-ranking | — |
| 26 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF FR | 47,922 | GGUF (inconnu) | image-text-to-text | ✓ |
| 27 | unsloth/Qwen-Image-2.1-GGUF FR | 47,222 | GGUF (inconnu) | text-to-image | ✓ |
| 28 | deepseek-ai/DeepSeek-V4.1-Flash FR | 45,395 | 763.2B | image-text-to-text | ✓ |
| 29 | ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF FR | 43,854 | 27.0B (GGUF) | text-generation | ✓ |
| 30 | JonathanColetti/Qwen3.8-27B-Uncensored-GGUF FR | 42,105 | 27.0B (GGUF) | text-generation | ✓ |
| 31 | openbmb/MiniCPM5-2B | 38,423 | 2.5B | text-generation | — |
| 32 | unsloth/Qwen3.8-27B-NVFP4 FR | 37,473 | 19.9B | other | ✓ |
| 33 | zai-org/GLM-5.3 FR | 36,625 | 753.3B | text-generation | ✓ |
| 34 | BAAI/bge-m3 FR | 33,674 | — | sentence-similarity | ✓ |
| 35 | empero-ai/Qwen3.8-35B-A3B-Distill-GGUF FR | 32,628 | 35.0B (GGUF) (MOE) MOE | text-generation | ✓ |
| 36 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 FR | 29,279 | 0.1B | sentence-similarity | ✓ |
| 37 | google/timesfm-3.0-pytorch | 27,622 | 0.3B | time-series-forecasting | — |
| 38 | mradermacher/Ornith-1.5-9B-uncensored-GGUF | 27,596 | 9.0B (GGUF) | conversational | — |
| 39 | unsloth/MiniMax-H3-GGUF | 27,487 | GGUF (inconnu) | image-text-to-video | — |
| 40 | Comfy-Org/z_image_turbo | 27,271 | — | image-to-image | — |
| 41 | lightx2v/Minimax-h3-Turbo | 23,732 | — | image-to-video | — |
| 42 | google-bert/bert-base-uncased | 21,842 | 0.1B | fill-mask | — |
| 43 | Lightricks/LTX-2.5 FR | 21,635 | — | image-to-video | ✓ |
| 44 | FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree | 21,230 | 35.0B | text-to-video | — |
| 45 | Viggle/Qwen-Image-2.1-viggle-turbo FR | 21,064 | 7.1B | text-to-image | ✓ |
| 46 | autotrust/JEV-9B | 20,702 | 9.0B | text-classification | — |
| 47 | google/gemma-4-E4B-it FR | 19,630 | 8.0B | any-to-any | ✓ |
| 48 | PrunaAI/Pruna-Qwen-Image-2.1 FR | 19,577 | — | text-to-image | ✓ |
| 49 | mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF | 18,555 | 9.0B (GGUF) | conversational | — |
| 50 | Qwen/Qwen3-Embedding-0.6B FR | 17,915 | 0.6B | feature-extraction | ✓ |
| 51 | WarmBloodAban/Minimax-h3_Singularity | 17,167 | — | image-to-video | — |
| 52 | hexgrad/Kokoro-82M | 16,688 | — | text-to-speech | — |
| 53 | MATLOWAI/minimax-h3-fused-turbo-int8-convrot | 16,518 | — | image-text-to-video | — |
| 54 | Comfy-Org/Wan_2.2_ComfyUI_Repackaged | 14,849 | — | image-to-video | — |
| 55 | google-t5/t5-small FR | 14,379 | 61.0MB | translation | ✓ |
| 56 | Mapika/decider-2b | 14,371 | 1.9B | text-classification | — |
| 57 | unsloth/embeddinggemma-2-GGUF FR | 13,861 | GGUF (inconnu) | feature-extraction | ✓ |
| 58 | google/gemma-4-E2B-it FR | 13,609 | 5.1B | any-to-any | ✓ |
| 59 | nomic-ai/nomic-embed-text-v1.5 | 13,249 | 0.1B | sentence-similarity | — |
| 60 | FastVideo/FastVideo-FastH3-Comfy | 13,202 | — | image-to-image | — |
| 61 | autotrust/JEV-27B | 12,574 | 26.9B | text-classification | — |
| 62 | pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF | 11,877 | GGUF (inconnu) | image-to-image | — |
| 63 | openai/clip-vit-base-patch32 | 11,809 | — | zero-shot-image-classification | — |
| 64 | google/gemma-4-12B-it FR | 11,753 | 12.0B | any-to-any | ✓ |
| 65 | Comfy-Org/YuE2 | 11,452 | — | image-to-image | — |
| 66 | pyannote/speaker-diarization-community-1 | 10,142 | — | automatic-speech-recognition | — |
| 67 | Comfy-Org/Ming-Image | 9,462 | — | image-to-image | — |
| 68 | intfloat/multilingual-e5-small FR | 8,970 | 0.1B | sentence-similarity | ✓ |
| 69 | BAAI/bge-large-en-v1.5 | 8,933 | 0.3B | feature-extraction | — |
| 70 | onnx-community/embeddinggemma-2-ONNX FR | 8,876 | — | feature-extraction | ✓ |
| 71 | nvidia/nemotron-3.5-asr-streaming-0.6b FR | 8,758 | 0.6B | automatic-speech-recognition | ✓ |
| 72 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice FR | 8,723 | 1.9B | text-to-speech | ✓ |
| 73 | openai/whisper-large-v3-turbo FR | 8,628 | 0.8B | automatic-speech-recognition | ✓ |
| 74 | google/embeddinggemma-300m FR | 8,034 | 0.3B | sentence-similarity | ✓ |
| 75 | Comfy-Org/Qwen3-VL FR | 8,004 | — | image-to-image | ✓ |
| 76 | Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1 FR | 7,975 | — | text-to-image | ✓ |
| 77 | fidel1234/Krea2_Asian_Character | 7,917 | — | image-to-image | — |
| 78 | k2-fsa/OmniVoice FR | 7,517 | 0.6B | text-to-speech | ✓ |
| 79 | nvidia/Cosmos3-Edge | 7,355 | 3.9B | other | — |
| 80 | mistralai/Voxtral-Mini-4B-Realtime-2602 FR | 7,345 | 4.4B | automatic-speech-recognition | ✓ |
| 81 | zai-org/GLM-OCR FR | 7,300 | 1.3B | image-to-text | ✓ |
| 82 | litert-community/gemma-4-E2B-it-litert-lm FR | 7,173 | 2.0B | other | ✓ |
| 83 | google/vit-base-patch16-224 | 7,142 | 87.0MB | image-classification | — |
| 84 | pyannote/speaker-diarization-3.1 | 6,636 | — | automatic-speech-recognition | — |
| 85 | audio-cpp/Yue2-3B-GGUF | 6,423 | 3.0B (GGUF) | text-to-audio | — |
| 86 | facebook/sam3 | 6,365 | 0.9B | mask-generation | — |
| 87 | unsloth/Qwen-Image-2.1-FP8 FR | 6,125 | — | text-to-image | ✓ |
| 88 | microsoft/TRELLIS.2-4B FR | 6,109 | 4.0B | image-to-3d | ✓ |
| 89 | coqui/XTTS-v2 | 6,102 | — | text-to-speech | — |
| 90 | google/gemma-4-12B-it-qat-q4_0-gguf FR | 6,067 | 12.0B (GGUF) | any-to-any | ✓ |
| 91 | ampixa/sanoTTS | 5,918 | — | text-to-speech | — |
| 92 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 FR | 5,805 | 0.3B | sentence-similarity | ✓ |
| 93 | pyannote/wespeaker-voxceleb-resnet34-LM | 5,734 | — | other | — |
| 94 | Qwen/Qwen3-VL-Embedding-8B FR | 5,374 | 8.1B | sentence-similarity | ✓ |
| 95 | fastino/GLiNER2.5-Decide | 5,058 | 0.5B | text-classification | — |
| 96 | Abiray/Qwen-Image-2.1-GGUF FR | 4,917 | GGUF (inconnu) | text-to-image | ✓ |
| 97 | Qwen/Qwen-Image-2.1 FR | 4,892 | 7.1B | text-to-image | ✓ |
| 98 | pyannote/segmentation-3.0 | 4,778 | — | voice-activity-detection | — |
| 99 | ibm-granite/granite-4.2-8b-GGUF | 4,715 | 8.0B (GGUF) | conversational | — |
| 100 | fastino/gliner2.5-multi-v1 FR | 4,690 | 0.3B | other | ✓ |
| 101 | Qwen/Qwen3-ASR-1.7B FR | 4,668 | 2.3B | automatic-speech-recognition | ✓ |
| 102 | Lightricks/LTX-2.3 FR | 4,434 | — | image-to-video | ✓ |
| 103 | ggml-org/embeddinggemma-2-GGUF FR | 4,211 | GGUF (inconnu) | feature-extraction | ✓ |
| 104 | Qwen/Qwen3-VL-Embedding-2B FR | 4,017 | 2.1B | sentence-similarity | ✓ |
| 105 | Winnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI | 3,871 | — | image-to-video | — |
| 106 | unsloth/gemma-4-12B-it-qat-GGUF FR | 3,773 | 12.0B (GGUF) | any-to-any | ✓ |
| 107 | tencent/Hy-MT2-7B-GGUF | 3,694 | 7.0B (GGUF) | conversational | — |
| 108 | stabilityai/stable-diffusion-xl-base-1.0 | 3,669 | 2.6B | text-to-image | — |
| 109 | openai/whisper-large-v3 FR | 3,604 | 1.5B | automatic-speech-recognition | ✓ |
| 110 | pottokao/Qwen-Image-2.1-PE-I2I-Heretic-GGUF FR | 3,567 | GGUF (inconnu) | conversational | ✓ |
| 111 | mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-GGUF FR | 3,554 | GGUF (inconnu) | conversational | ✓ |
| 112 | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive FR | 3,239 | 9.0B | conversational | ✓ |
| 113 | Qwen/Qwen3-ASR-1.7B-hf FR | 3,220 | 2.0B | automatic-speech-recognition | ✓ |
| 114 | larryvrh/MiniMax-H3-Turbo-Lora | 3,189 | — | text-to-video | — |
| 115 | drbaph/MiniMax-H3-Turbo-Lora-ComfyUI | 3,088 | — | text-to-video | — |
| 116 | openbmb/VoxCPM2 FR | 3,085 | 2.3B | text-to-speech | ✓ |
| 117 | litert-community/embeddinggemma-2-740m-litert-lm FR | 3,045 | — | other | ✓ |
| 118 | unsloth/gemma-4-E4B-it-qat-GGUF FR | 2,951 | 4.0B (GGUF) | any-to-any | ✓ |
| 119 | QuantFunc/Minimax-H3-Quantfunc-4bit | 2,876 | 4.0B | text-to-video | — |
| 120 | google/gemma-4-E4B FR | 2,796 | 8.0B | any-to-any | ✓ |
| 121 | 0xSojalSec/Qwen-Image-2.1-Uncensored-GGUF FR | 2,640 | GGUF (inconnu) | text-to-image | ✓ |
| 122 | nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF FR | 2,496 | 27.0B (GGUF) | conversational | ✓ |
| 123 | google/gemma-4-E2B-it-qat-q4_0-gguf FR | 2,334 | 2.0B (GGUF) | any-to-any | ✓ |
| 124 | akatz-ai/MiniMax-H3-Character-Swap-LoRA | 2,271 | — | video-to-video | — |
| 125 | Edge0/Audio8-ASR-Infinite | 2,260 | 4.1B | automatic-speech-recognition | — |
| 126 | Qwen/Qwen3-TTS-12Hz-0.6B-Base FR | 2,245 | 0.9B | text-to-speech | ✓ |
| 127 | ai-sage/GigaAM-v3 | 2,231 | — | automatic-speech-recognition | — |
| 128 | tencent/Hy-MT2-1.8B-GGUF | 2,153 | 1.8B (GGUF) | conversational | — |
| 129 | bartowski/TheDrummer_Artemis-31B-v1.2-GGUF | 2,012 | 31.0B (GGUF) | any-to-any | — |
| 130 | autotrust/JEV-Gemma4-26B-A4B FR | 1,994 | 25.8B / 4.0B MOE | text-classification | ✓ |
| 131 | ggml-org/Bespoke-Nimble-9B-v3-GGUF | 1,994 | 9.0B (GGUF) | zero-shot-classification | — |
| 132 | convaiinnovations/laya | 1,975 | 0.4B | text-classification | — |
| 133 | nvidia/Nemotron-3-Diarization | 1,823 | 99.0MB | voice-activity-detection | — |
| 134 | Serveurperso/Qwen3-TTS-GGUF FR | 1,780 | GGUF (inconnu) | text-to-speech | ✓ |
| 135 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,726 | 0.3B | image-feature-extraction | — |
| 136 | microsoft/VibeVoice-1.5B FR | 1,690 | 2.7B | text-to-speech | ✓ |
| 137 | speach1sdef178/MiniMax-H3-X2-Detail-VAE | 1,628 | — | image-to-video | — |
| 138 | ggml-org/Kev-4B-GGUF | 1,582 | 4.0B (GGUF) | text-classification | — |
| 139 | IndexTeam/Index-Translate-9B-GGUF | 1,537 | 9.0B (GGUF) | translation | — |
| 140 | Mapika/decider-4b | 1,515 | 4.2B | text-classification | — |
| 141 | OpenMOSS-Team/MOSS-Transcribe-Diarize FR | 1,493 | 0.9B | audio-text-to-text | ✓ |
| 142 | madebyollin/texture-fix-vae-for-qwen-image-2.1 FR | 1,433 | 0.3B | other | ✓ |
| 143 | turboderp/Qwen3.8-27B-exl3 FR | 1,420 | 27.0B | other | ✓ |
| 144 | ggml-org/Laya-GGUF | 1,386 | GGUF (inconnu) | text-classification | — |
| 145 | fal/MiniMax-H3-Realism-People-LoRA | 1,366 | — | image-text-to-video | — |
| 146 | m-a-p/YuE2-3B | 1,234 | 3.6B | text-to-audio | — |
| 147 | alibaba-pai/MiniMax-H3-Acc-LoRAs | 1,213 | — | text-to-video | — |
| 148 | facebook/dinov3-vitb16-pretrain-lvd1689m | 1,205 | 86.0MB | image-feature-extraction | — |
| 149 | google/embeddinggemma-2 FR | 1,167 | 0.7B | feature-extraction | ✓ |
| 150 | dealignai/GLM-5.3-Flash-UNCENSORED-FP8 | 1,115 | 321.3B | other | — |
| 151 | google/gemma-4-E2B FR | 1,076 | 5.1B | any-to-any | ✓ |
| 152 | pablodawson/MiniMax-H3-360-Orbit-LoRA | 1,004 | — | image-text-to-video | — |
| 153 | QuantStack/Wan2.2-I2V-A14B-GGUF | 1,000 | 14.0B (GGUF) | image-to-video | — |
| 154 | drbaph/Hyperflow-Comfyui | 987 | — | image-text-to-video | — |
| 155 | IndexTeam/Index-Translate-2B-GGUF | 947 | 2.0B (GGUF) | translation | — |
| 156 | ibm-granite/granite-embedding-311m-multilingual-r2 FR | 946 | 0.3B | feature-extraction | ✓ |
| 157 | fastino/GLiNER2.5-multi-Decide FR | 929 | 0.3B | other | ✓ |
| 158 | Lightricks/LTX-Video | 895 | 1.9B | image-to-video | — |
| 159 | m-a-p/SheetSage2 | 853 | 57.0MB | feature-extraction | — |
| 160 | Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details | 704 | 22.0B | video-to-video | — |
| 161 | m-a-p/MERT-v2-FullSong | 686 | 0.6B | feature-extraction | — |
| 162 | pixai-labs/pixai-tagger-v1.0 | 672 | 0.5B | image-classification | — |
| 163 | Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen | 636 | 22.0B | video-to-video | — |
| 164 | nvidia/personaplex-7b-v1 | 632 | 8.4B | audio-to-audio | — |
| 165 | SulphurAI/Sulphur-2-base | 628 | — | text-to-video | — |
| 166 | realrebelai/LTX-2.5_GGUFs | 612 | GGUF (inconnu) | text-to-video | — |
| 167 | Iwannapose/minimax_h3_pdmd_2nfe_comfyui | 589 | — | text-to-video | — |
| 168 | Lightricks/LTX-2.5-Diffusers FR | 587 | 19.0B | text-to-video | ✓ |
| 169 | Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview | 576 | — | text-to-video | — |
| 170 | briaai/RMBG-2.0 | 570 | 0.2B | image-segmentation | — |
| 171 | unsloth/embeddinggemma-2 FR | 561 | 0.7B | feature-extraction | ✓ |
| 172 | IndexTeam/Index-Translate-35B-A3B-preview-GGUF | 554 | 35.0B (GGUF) (MOE) MOE | translation | — |
| 173 | facebook/dinov3-vits16-pretrain-lvd1689m | 548 | 22.0MB | image-feature-extraction | — |
| 174 | mlx-community/clef-flash-4bit | 513 | 9.4B | zero-shot-classification | — |
| 175 | ggml-org/lev-GGUF | 472 | GGUF (inconnu) | zero-shot-classification | — |
| 176 | stabilityai/stable-audio-3-medium | 428 | 2.3B | text-to-audio | — |
| 177 | Viggle/Viggle-Animate | 410 | 33.1B | video-to-video | — |
| 178 | LiquidAI/LFM2.5-Encoder-350M FR | 402 | 0.4B | fill-mask | ✓ |
| 179 | Lightricks/LTX-2.5-22b-IC-LoRA-SDR-To-HDR | 392 | 22.0B | video-to-video | — |
| 180 | videorebirth/hyperflow | 379 | — | image-text-to-video | — |
| 181 | Prior-Labs/tabpfn_3_5 | 372 | — | tabular-classification | — |
| 182 | akatz-ai/MiniMax-H3-Person-Remover-LoRA | 328 | — | video-to-video | — |
| 183 | Lightricks/LTX-2.5-22b-IC-LoRA-Restore | 324 | 22.0B | video-to-video | — |
| 184 | openjev/openjev FR | 305 | 27.4B | zero-shot-classification | ✓ |
| 185 | ACE-Step/Ace-Step1.5 | 264 | — | text-to-audio | — |
| 186 | Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render | 261 | 22.0B | video-to-video | — |
| 187 | stabilityai/stable-audio-3-small-sfx | 259 | 0.6B | text-to-audio | — |
| 188 | facebook/sam3.1 | 256 | — | mask-generation | — |
| 189 | vllm-sr/Decision-2.0-Vega-27B | 246 | 27.0B | zero-shot-classification | — |
| 190 | jhu-clsp/mmBERT-small | 238 | — | fill-mask | — |
| 191 | Contrastive-LM/CLM-v0.1-8B | 235 | 8.0B | text-ranking | — |
| 192 | tencent/Hy-MT2-1.8B FR | 209 | 2.0B | translation | ✓ |
| 193 | numind/NuExtract3 FR | 187 | 4.5B | image-to-text | ✓ |
| 194 | PSRben/VisionHOPE | 183 | — | image-classification | — |
| 195 | Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler | 143 | 22.0B | video-to-video | — |
| 196 | facebook/dinov3-vitl16-pretrain-sat493m | 133 | 0.3B | image-feature-extraction | — |
| 197 | tencent/Hunyuan3D-2.1 | 124 | — | image-to-3d | — |
| 198 | vllm-sr/Decision-2.0-Kai-0.6B | 118 | 0.6B | zero-shot-classification | — |
| 199 | vllm-sr/Decision-2.0-Nox-4B | 116 | 4.0B | zero-shot-classification | — |
| 200 | IndexTeam/Index-Translate-2B | 112 | 2.3B | translation | — |
| 201 | MiniMaxAI/MiniMax-Music3 | 112 | 2.4B | text-to-audio | — |
| 202 | MahmoodLab/UNI2-h | 110 | — | image-feature-extraction | — |
| 203 | black-forest-labs/flux-3-action-so101 FR | 99 | 6.9B | robotics | ✓ |
| 204 | MATLOWAI/MiniMax-H3-Motion-Adapter | 98 | — | image-to-video | — |
| 205 | IndexTeam/Index-Translate-9B | 96 | 9.7B | translation | — |
| 206 | black-forest-labs/flux-3-action-droid FR | 87 | 6.9B | robotics | ✓ |
| 207 | vllm-sr/Decision-2.0-Sol-2B | 76 | 2.0B | zero-shot-classification | — |
| 208 | vllm-sr/Decision-2.0-Lux-9B | 75 | 9.0B | zero-shot-classification | — |
| 209 | vllm-sr/Vela-2.0-0.3B FR | 72 | 0.3B | zero-shot-classification | ✓ |
| 210 | Ultralytics/YOLO26 FR | 72 | — | object-detection | ✓ |
| 211 | Lightricks/LTX-2.5-22b-IC-LoRA-Day-To-Night | 66 | 22.0B | video-to-video | — |
| 212 | black-forest-labs/flux-3-action-base FR | 60 | — | robotics | ✓ |
| 213 | netease-youdao/Confucius4-T3PO | 51 | 14.8B | translation | — |
| 214 | neuphonic/neudecide | 48 | — | audio-classification | — |
| 215 | MahmoodLab/UNI | 46 | — | image-feature-extraction | — |
| 216 | nvidia/RE-USE | 44 | 10.0MB | audio-to-audio | — |
| 217 | stabilityai/stable-fast-3d | 39 | 1.0B | image-to-3d | — |
| 218 | birlaailabs/yug | 37 | 0.3B | time-series-forecasting | — |
| 219 | bodhan-ai/indic-ocr | 23 | — | image-to-text | — |
| 220 | stabilityai/stable-audio-open-1.0 | 21 | 1.2B | text-to-audio | — |
| 221 | interfaze-ai/interfaze-1-lite FR | 19 | — | image-text-to-image | ✓ |
| 222 | nvidia/music-flamingo-hf | 14 | 8.3B | audio-text-to-text | — |
| 223 | stabilityai/stable-point-aware-3d | 13 | 2.0B | image-to-3d | — |
| 224 | desert-ant-labs/clear | 12 | — | audio-to-audio | — |
| 225 | facebook/VGGT-1B-Commercial | 7 | 1.3B | image-to-3d | — |
| 226 | nvidia/Lyra-2.0 | 5 | — | image-to-3d | — |
| 227 | HuggingFaceBio/Carbon-A-1.2B | 4 | 1.2B | token-classification | — |
| 228 | MeteoSwiss/Varda-single-1.0 | 0 | — | graph-ml | — |
| 229 | NU-World-Model-Embodied-AI/phyjudge-9B | 0 | 9.0B | video-text-to-text | — |
| 230 | nvidia/PixelUMM | 0 | — | image-to-text | — |
| 231 | spellbrush/kyaraembed | 0 | — | audio-classification | — |
| 232 | TencentARC/Pixal3D | 0 | — | image-to-3d | — |
| 233 | niclasclassen/robustness-of-transferability-estimation-metrics-for-medical-imaging | 0 | — | image-classification | — |
| 234 | Kukulauren/3D_medical_imaging_dental | 0 | 6.0MB | image-segmentation | — |
| 235 | marcelosantoskuw/paper_015153151_visual_question_answering | 0 | — | visual-question-answering | — |
| 236 | yang-ai-lab/OpenSLA | 0 | — | question-answering | — |