245 modèles dans 41 catégories | Généré le 07/10/2026 22:33 UTC
245 modèles sélectionnés
| # | Modele | DL/Jour | Params | pipeline | FR |
|---|---|---|---|---|---|
| 1 | Comfy-Org/MiniMax-H3 | 344,031 | — | image-to-image | — |
| 2 | Comfy-Org/Qwen-Image-2.1 FR | 327,139 | — | image-to-image | ✓ |
| 3 | autotrust/JEV-27B-VL | 218,459 | 27.8B | image-text-to-text | — |
| 4 | prism-ml/Ternary-Bonsai-2-27B-gguf | 213,573 | 27.0B (GGUF) | text-generation | — |
| 5 | autotrust/GEV-26B-Decide | 179,173 | 25.8B | text-classification | — |
| 6 | zai-org/GLM-5.3-Flash FR | 143,274 | 321.3B | image-text-to-text | ✓ |
| 7 | sentence-transformers/all-MiniLM-L6-v2 | 139,378 | 23.0MB | sentence-similarity | — |
| 8 | unsloth/Qwen3.8-27B-GGUF FR | 119,146 | 27.0B (GGUF) | conversational | ✓ |
| 9 | Qwen/Qwen3.8-27B FR | 107,286 | 27.8B | image-text-to-text | ✓ |
| 10 | abenzerps/Qwen-Image-2.1-Uncensored-GGUF FR | 107,096 | GGUF (inconnu) | text-to-image | ✓ |
| 11 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF FR | 102,671 | GGUF (inconnu) | image-text-to-text | ✓ |
| 12 | ornith-ai/Ornith-1.5-9B-GGUF | 102,542 | 9.0B (GGUF) | text-generation | — |
| 13 | SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF FR | 100,145 | GGUF (inconnu) | image-text-to-text | ✓ |
| 14 | mudler/locate-anything.cpp-gguf | 97,662 | GGUF (inconnu) | object-detection | — |
| 15 | Qwen/Qwen3.8-27B-FP8 FR | 86,755 | 27.8B | image-text-to-text | ✓ |
| 16 | ornith-ai/Ornith-1.5-35B-A3B-GGUF | 71,849 | 35.0B (GGUF) (MOE) MOE | text-generation | — |
| 17 | audio-cpp/audio.cpp-gguf | 71,846 | GGUF (inconnu) | text-to-speech | — |
| 18 | Comfy-Org/Krea-2 | 70,148 | — | image-to-image | — |
| 19 | deepseek-ai/DeepSeek-V4-Flash-0731 FR | 66,596 | 304.2B | text-generation | ✓ |
| 20 | amazon/chronos-2 | 63,693 | 0.1B | time-series-forecasting | — |
| 21 | google/gemma-4-26B-A4B-it FR | 59,396 | 25.8B / 4.0B MOE | image-text-to-text | ✓ |
| 22 | Qwen/Qwen3-0.6B FR | 58,943 | 0.8B | text-generation | ✓ |
| 23 | DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF FR | 58,015 | 27.0B (GGUF) | image-text-to-text | ✓ |
| 24 | MiniMaxAI/MiniMax-H3 | 50,894 | 33.1B | image-text-to-video | — |
| 25 | ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF FR | 50,335 | GGUF (inconnu) | image-text-to-text | ✓ |
| 26 | cross-encoder/ms-marco-MiniLM-L6-v2 | 49,575 | 23.0MB | text-ranking | — |
| 27 | unsloth/Qwen-Image-2.1-GGUF FR | 46,542 | GGUF (inconnu) | text-to-image | ✓ |
| 28 | deepseek-ai/DeepSeek-V4.1-Flash FR | 46,500 | 763.2B | image-text-to-text | ✓ |
| 29 | ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF FR | 43,035 | 27.0B (GGUF) | text-generation | ✓ |
| 30 | JonathanColetti/Qwen3.8-27B-Uncensored-GGUF FR | 42,756 | 27.0B (GGUF) | text-generation | ✓ |
| 31 | nvidia/Qwen3.6-35B-A3B-NVFP4 FR | 41,089 | 18.7B / 3.0B MOE | text-generation | ✓ |
| 32 | unsloth/Qwen3.8-27B-NVFP4 FR | 40,452 | 19.9B | other | ✓ |
| 33 | openbmb/MiniCPM5-2B | 39,805 | 2.5B | text-generation | — |
| 34 | zai-org/GLM-5.3 FR | 35,065 | 753.3B | text-generation | ✓ |
| 35 | BAAI/bge-m3 FR | 34,386 | — | sentence-similarity | ✓ |
| 36 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 FR | 29,978 | 0.1B | sentence-similarity | ✓ |
| 37 | Comfy-Org/z_image_turbo | 27,699 | — | image-to-image | — |
| 38 | unsloth/MiniMax-H3-GGUF | 27,375 | GGUF (inconnu) | image-text-to-video | — |
| 39 | google/timesfm-3.0-pytorch | 27,166 | 0.3B | time-series-forecasting | — |
| 40 | mradermacher/Ornith-1.5-9B-uncensored-GGUF | 26,764 | 9.0B (GGUF) | conversational | — |
| 41 | FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree | 25,124 | 35.0B | text-to-video | — |
| 42 | lightx2v/Minimax-h3-Turbo | 24,774 | — | image-to-video | — |
| 43 | google-bert/bert-base-uncased | 22,921 | 0.1B | fill-mask | — |
| 44 | autotrust/JEV-9B | 22,866 | 9.0B | text-classification | — |
| 45 | Lightricks/LTX-2.5 FR | 22,030 | — | image-to-video | ✓ |
| 46 | Viggle/Qwen-Image-2.1-viggle-turbo FR | 21,787 | 7.1B | text-to-image | ✓ |
| 47 | MATLOWAI/minimax-h3-fused-turbo-int8-convrot | 20,519 | — | image-text-to-video | — |
| 48 | google/gemma-4-E4B-it FR | 20,181 | 8.0B | any-to-any | ✓ |
| 49 | PrunaAI/Pruna-Qwen-Image-2.1 FR | 18,603 | — | text-to-image | ✓ |
| 50 | Qwen/Qwen3-Embedding-0.6B FR | 18,555 | 0.6B | feature-extraction | ✓ |
| 51 | WarmBloodAban/Minimax-h3_Singularity | 17,652 | — | image-to-video | — |
| 52 | hexgrad/Kokoro-82M | 17,149 | — | text-to-speech | — |
| 53 | mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF | 16,898 | 9.0B (GGUF) | conversational | — |
| 54 | Mapika/decider-2b | 15,485 | 1.9B | text-classification | — |
| 55 | Comfy-Org/Wan_2.2_ComfyUI_Repackaged | 15,030 | — | image-to-video | — |
| 56 | google-t5/t5-small FR | 14,617 | 61.0MB | translation | ✓ |
| 57 | autotrust/JEV-27B | 14,260 | 26.9B | text-classification | — |
| 58 | google/gemma-4-E2B-it FR | 13,726 | 5.1B | any-to-any | ✓ |
| 59 | nomic-ai/nomic-embed-text-v1.5 | 13,456 | 0.1B | sentence-similarity | — |
| 60 | FastVideo/FastVideo-FastH3-Comfy | 12,898 | — | image-to-image | — |
| 61 | google/gemma-4-12B-it FR | 12,683 | 12.0B | any-to-any | ✓ |
| 62 | pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF | 12,668 | GGUF (inconnu) | image-to-image | — |
| 63 | unsloth/embeddinggemma-2-GGUF FR | 11,470 | GGUF (inconnu) | feature-extraction | ✓ |
| 64 | Comfy-Org/YuE2 | 11,434 | — | image-to-image | — |
| 65 | pyannote/speaker-diarization-community-1 | 10,287 | — | automatic-speech-recognition | — |
| 66 | Comfy-Org/Ming-Image | 10,283 | — | image-to-image | — |
| 67 | intfloat/multilingual-e5-small FR | 9,262 | 0.1B | sentence-similarity | ✓ |
| 68 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice FR | 9,003 | 1.9B | text-to-speech | ✓ |
| 69 | nvidia/nemotron-3.5-asr-streaming-0.6b FR | 8,883 | 0.6B | automatic-speech-recognition | ✓ |
| 70 | BAAI/bge-base-en-v1.5 | 8,683 | 0.1B | feature-extraction | — |
| 71 | openai/whisper-large-v3-turbo FR | 8,625 | 0.8B | automatic-speech-recognition | ✓ |
| 72 | nvidia/Cosmos3-Edge | 8,454 | 3.9B | other | — |
| 73 | google/embeddinggemma-300m FR | 8,110 | 0.3B | sentence-similarity | ✓ |
| 74 | ornith-ai/Ornith-1.5-35B-A3B-DFlash | 8,060 | 0.4B / 3.0B MOE | other | — |
| 75 | fidel1234/Krea2_Asian_Character | 7,785 | — | image-to-image | — |
| 76 | Bingsu/adetailer | 7,668 | — | other | — |
| 77 | k2-fsa/OmniVoice FR | 7,626 | 0.6B | text-to-speech | ✓ |
| 78 | autotrust/GEV-26B-Decide-NVFP4 | 7,478 | 14.4B | text-classification | — |
| 79 | mistralai/Voxtral-Mini-4B-Realtime-2602 FR | 7,417 | 4.4B | automatic-speech-recognition | ✓ |
| 80 | zai-org/GLM-OCR FR | 7,379 | 1.3B | image-to-text | ✓ |
| 81 | litert-community/gemma-4-E2B-it-litert-lm FR | 7,245 | 2.0B | other | ✓ |
| 82 | Comfy-Org/Pixal3D | 6,948 | — | image-to-image | — |
| 83 | Noctaluna/Noct-Q-Uncensored-Qwen-Image-2.1 FR | 6,928 | — | text-to-image | ✓ |
| 84 | pyannote/speaker-diarization-3.1 | 6,773 | — | automatic-speech-recognition | — |
| 85 | google/vit-base-patch16-224 | 6,579 | 87.0MB | image-classification | — |
| 86 | audio-cpp/Yue2-3B-GGUF | 6,513 | 3.0B (GGUF) | text-to-audio | — |
| 87 | facebook/sam3 | 6,510 | 0.9B | mask-generation | — |
| 88 | unsloth/Qwen-Image-2.1-FP8 FR | 6,499 | — | text-to-image | ✓ |
| 89 | google/gemma-4-12B-it-qat-q4_0-gguf FR | 6,319 | 12.0B (GGUF) | any-to-any | ✓ |
| 90 | coqui/XTTS-v2 | 6,249 | — | text-to-speech | — |
| 91 | microsoft/TRELLIS.2-4B FR | 6,068 | 4.0B | image-to-3d | ✓ |
| 92 | ornith-ai/Ornith-1.5-9B-DFlash | 5,561 | 1.3B | other | — |
| 93 | Qwen/Qwen3-ASR-1.7B FR | 5,275 | 2.3B | automatic-speech-recognition | ✓ |
| 94 | wfzyx/von | 5,201 | 0.4B | zero-shot-classification | — |
| 95 | fastino/GLiNER2.5-Decide | 5,178 | 0.5B | token-classification | — |
| 96 | Abiray/Qwen-Image-2.1-GGUF FR | 5,155 | GGUF (inconnu) | text-to-image | ✓ |
| 97 | fastino/gliner2.5-multi-v1 FR | 4,923 | 0.3B | token-classification | ✓ |
| 98 | Lightricks/LTX-2.3 FR | 4,899 | — | image-to-video | ✓ |
| 99 | pyannote/segmentation-3.0 | 4,882 | — | voice-activity-detection | — |
| 100 | Qwen/Qwen-Image-2.1 FR | 4,752 | 7.1B | text-to-image | ✓ |
| 101 | Winnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI | 4,201 | — | image-to-video | — |
| 102 | unsloth/gemma-4-12B-it-qat-GGUF FR | 4,198 | 12.0B (GGUF) | any-to-any | ✓ |
| 103 | Qwen/Qwen3-VL-Embedding-2B FR | 4,185 | 2.1B | sentence-similarity | ✓ |
| 104 | pottokao/Qwen-Image-2.1-PE-I2I-Heretic-GGUF FR | 3,910 | GGUF (inconnu) | conversational | ✓ |
| 105 | ggml-org/embeddinggemma-2-GGUF FR | 3,842 | GGUF (inconnu) | feature-extraction | ✓ |
| 106 | openai/whisper-large-v3 FR | 3,751 | 1.5B | automatic-speech-recognition | ✓ |
| 107 | stabilityai/stable-diffusion-xl-base-1.0 | 3,737 | 2.6B | text-to-image | — |
| 108 | drbaph/Viggle-Animate-ComfyUI | 3,541 | — | video-to-video | — |
| 109 | mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-GGUF FR | 3,485 | GGUF (inconnu) | conversational | ✓ |
| 110 | QuantFunc/Minimax-H3-Quantfunc-4bit | 3,371 | 4.0B | text-to-video | — |
| 111 | larryvrh/MiniMax-H3-Turbo-Lora | 3,324 | — | text-to-video | — |
| 112 | unsloth/gemma-4-E4B-it-qat-GGUF FR | 3,306 | 4.0B (GGUF) | any-to-any | ✓ |
| 113 | Qwen/Qwen3-ASR-1.7B-hf FR | 3,294 | 2.0B | automatic-speech-recognition | ✓ |
| 114 | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive FR | 3,294 | 9.0B | conversational | ✓ |
| 115 | drbaph/MiniMax-H3-Turbo-Lora-ComfyUI | 3,197 | — | text-to-video | — |
| 116 | ResembleAI/chatterbox FR | 3,078 | — | text-to-speech | ✓ |
| 117 | openbmb/VoxCPM2 FR | 2,918 | 2.3B | text-to-speech | ✓ |
| 118 | nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF FR | 2,859 | 27.0B (GGUF) | conversational | ✓ |
| 119 | google/gemma-4-E4B FR | 2,804 | 8.0B | any-to-any | ✓ |
| 120 | 0xSojalSec/Qwen-Image-2.1-Uncensored-GGUF FR | 2,655 | GGUF (inconnu) | text-to-image | ✓ |
| 121 | ggml-org/Bespoke-Nimble-9B-v3-GGUF | 2,650 | 9.0B (GGUF) | zero-shot-classification | — |
| 122 | Edge0/Audio8-ASR-Infinite | 2,531 | 4.1B | automatic-speech-recognition | — |
| 123 | mistralai/Mistral-7B-Instruct-v0.3 | 2,449 | 7.2B | other | — |
| 124 | onnx-community/embeddinggemma-2-ONNX FR | 2,356 | — | feature-extraction | ✓ |
| 125 | Qwen/Qwen3-TTS-12Hz-0.6B-Base FR | 2,278 | 0.9B | text-to-speech | ✓ |
| 126 | tencent/Hy-MT2-1.8B-GGUF | 2,249 | 1.8B (GGUF) | conversational | — |
| 127 | ai-sage/GigaAM-v3 | 2,176 | — | automatic-speech-recognition | — |
| 128 | bartowski/TheDrummer_Artemis-31B-v1.2-GGUF | 2,046 | 31.0B (GGUF) | any-to-any | — |
| 129 | openai/privacy-filter | 1,998 | 1.4B | token-classification | — |
| 130 | akatz-ai/MiniMax-H3-Character-Swap-LoRA | 1,955 | — | video-to-video | — |
| 131 | speach1sdef178/MiniMax-H3-X2-Detail-VAE | 1,823 | — | image-to-video | — |
| 132 | Serveurperso/Qwen3-TTS-GGUF FR | 1,773 | GGUF (inconnu) | text-to-speech | ✓ |
| 133 | microsoft/VibeVoice-1.5B FR | 1,744 | 2.7B | text-to-speech | ✓ |
| 134 | nvidia/Nemotron-3-Diarization | 1,729 | 99.0MB | voice-activity-detection | — |
| 135 | Lucebox/DeepSeek-V4.1-Flash-ROCMFP23-GGUF FR | 1,708 | GGUF (inconnu) | other | ✓ |
| 136 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,680 | 0.3B | image-feature-extraction | — |
| 137 | Mapika/decider-4b | 1,655 | 4.2B | text-classification | — |
| 138 | OpenMOSS-Team/MOSS-Transcribe-Diarize FR | 1,546 | 0.9B | audio-text-to-text | ✓ |
| 139 | autotrust/JEV-Gemma4-26B-A4B FR | 1,511 | 25.8B / 4.0B MOE | text-classification | ✓ |
| 140 | ggml-org/Laya-GGUF | 1,507 | GGUF (inconnu) | text-classification | — |
| 141 | convaiinnovations/laya | 1,500 | 0.4B | text-classification | — |
| 142 | turboderp/Qwen3.8-27B-exl3 FR | 1,470 | 27.0B | other | ✓ |
| 143 | BeaverAI/Spectre-37B-v1a-GGUF | 1,424 | 37.0B (GGUF) | conversational | — |
| 144 | fal/MiniMax-H3-Realism-People-LoRA | 1,389 | — | image-text-to-video | — |
| 145 | ggml-org/Kev-4B-GGUF | 1,362 | 4.0B (GGUF) | text-classification | — |
| 146 | IndexTeam/Index-Translate-9B-GGUF | 1,341 | 9.0B (GGUF) | translation | — |
| 147 | alibaba-pai/MiniMax-H3-Acc-LoRAs | 1,338 | — | text-to-video | — |
| 148 | madebyollin/texture-fix-vae-for-qwen-image-2.1 FR | 1,335 | 0.3B | other | ✓ |
| 149 | fastino/gliner2-privacy-filter-PII-multi FR | 1,321 | 0.3B | token-classification | ✓ |
| 150 | m-a-p/YuE2-3B | 1,276 | 3.6B | text-to-audio | — |
| 151 | alibaba-pai/MiniMax-H3-Fun-Controlnet-Union-2.0 | 1,266 | — | text-to-video | — |
| 152 | facebook/dinov3-vitb16-pretrain-lvd1689m | 1,218 | 86.0MB | image-feature-extraction | — |
| 153 | SulphurAI/Sulphur-2-base | 1,082 | — | text-to-video | — |
| 154 | drbaph/Hyperflow-Comfyui | 1,081 | — | image-text-to-video | — |
| 155 | google/gemma-4-E2B FR | 1,070 | 5.1B | any-to-any | ✓ |
| 156 | pablodawson/MiniMax-H3-360-Orbit-LoRA | 1,012 | — | image-text-to-video | — |
| 157 | fastino/GLiNER2.5-multi-Decide FR | 1,004 | 0.3B | token-classification | ✓ |
| 158 | ibm-granite/granite-embedding-311m-multilingual-r2 FR | 988 | 0.3B | feature-extraction | ✓ |
| 159 | QuantStack/Wan2.2-I2V-A14B-GGUF | 978 | 14.0B (GGUF) | image-to-video | — |
| 160 | IndexTeam/Index-Translate-2B-GGUF | 965 | 2.0B (GGUF) | translation | — |
| 161 | HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive FR | 899 | 4.0B | conversational | ✓ |
| 162 | m-a-p/SheetSage2 | 884 | 57.0MB | feature-extraction | — |
| 163 | google/gemma-4-12B FR | 774 | 12.0B | any-to-any | ✓ |
| 164 | pixai-labs/pixai-tagger-v1.0 | 692 | 0.5B | image-classification | — |
| 165 | Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details | 689 | 22.0B | video-to-video | — |
| 166 | Lightricks/LTX-2.5-Diffusers FR | 669 | 19.0B | text-to-video | ✓ |
| 167 | nvidia/personaplex-7b-v1 | 655 | 8.4B | audio-to-audio | — |
| 168 | facebook/dinov3-vits16-pretrain-lvd1689m | 644 | 22.0MB | image-feature-extraction | — |
| 169 | manjunathshiva/opendecider-nano | 623 | 0.4B | zero-shot-classification | — |
| 170 | unsloth/embeddinggemma-2 FR | 622 | 0.7B | feature-extraction | ✓ |
| 171 | briaai/RMBG-2.0 | 610 | 0.2B | image-segmentation | — |
| 172 | Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen | 584 | 22.0B | video-to-video | — |
| 173 | Iwannapose/minimax_h3_pdmd_2nfe_comfyui | 566 | — | text-to-video | — |
| 174 | mlx-community/clef-flash-4bit | 556 | 9.4B | zero-shot-classification | — |
| 175 | ggml-org/lev-GGUF | 536 | GGUF (inconnu) | zero-shot-classification | — |
| 176 | Viggle/Viggle-Animate | 524 | 33.1B | video-to-video | — |
| 177 | Iwannapose/minimax_h3_pdmd_4nfe_comfyui | 499 | — | text-to-video | — |
| 178 | IndexTeam/Index-Translate-35B-A3B-preview-GGUF | 476 | 35.0B (GGUF) (MOE) MOE | translation | — |
| 179 | Jojocodex/wushu-action-v7-minimax-h3-fl2va-ref2va-lora | 472 | — | image-to-video | — |
| 180 | stabilityai/stable-audio-3-medium | 427 | 2.3B | text-to-audio | — |
| 181 | Lightricks/LTX-2.5-22b-IC-LoRA-SDR-To-HDR | 422 | 22.0B | video-to-video | — |
| 182 | czl/CLM-v0.1-8B-GGUF | 402 | 8.0B (GGUF) | text-ranking | — |
| 183 | mlx-community/embeddinggemma-2-bf16 FR | 380 | 0.7B | feature-extraction | ✓ |
| 184 | Prior-Labs/tabpfn_3_5 | 377 | — | tabular-classification | — |
| 185 | openjev/openjev FR | 334 | 27.4B | zero-shot-classification | ✓ |
| 186 | google/embeddinggemma-2 FR | 329 | 0.7B | feature-extraction | ✓ |
| 187 | Abiray/10Eros-Max-Turbo-Hybrid-Beta5-GGUF | 328 | GGUF (inconnu) | image-text-to-video | — |
| 188 | Lightricks/LTX-2.5-22b-IC-LoRA-Restore | 290 | 22.0B | video-to-video | — |
| 189 | briaai/RMBG-1.4 | 274 | 44.0MB | image-segmentation | — |
| 190 | Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients | 267 | 22.0B | video-to-video | — |
| 191 | jeff-legacy/Jeff-Qwen3.5-0.8B FR | 265 | 0.9B | zero-shot-classification | ✓ |
| 192 | facebook/sam3.1 | 264 | — | mask-generation | — |
| 193 | ACE-Step/Ace-Step1.5 | 263 | — | text-to-audio | — |
| 194 | Contrastive-LM/CLM-v0.1-8B | 253 | 8.0B | text-ranking | — |
| 195 | stabilityai/stable-audio-3-small-sfx | 247 | 0.6B | text-to-audio | — |
| 196 | jhu-clsp/mmBERT-small | 229 | — | fill-mask | — |
| 197 | PSRben/VisionHOPE | 225 | — | image-classification | — |
| 198 | tencent/Hy-MT2-1.8B FR | 216 | 2.0B | translation | ✓ |
| 199 | Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render | 198 | 22.0B | video-to-video | — |
| 200 | mlx-community/clef-4bit | 198 | 27.4B | zero-shot-classification | — |
| 201 | numind/NuExtract3 FR | 195 | 4.5B | image-to-text | ✓ |
| 202 | mlx-community/clef-8bit | 191 | 27.4B | zero-shot-classification | — |
| 203 | MATLOWAI/MiniMax-H3-ORB360-CardSpin | 164 | — | image-to-video | — |
| 204 | fastino/GLiNER2.5-Decide-1B | 161 | 1.2B | token-classification | — |
| 205 | Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler | 148 | 22.0B | video-to-video | — |
| 206 | tencent/Hunyuan3D-2.1 | 124 | — | image-to-3d | — |
| 207 | MiniMaxAI/MiniMax-Music3 | 120 | 2.4B | text-to-audio | — |
| 208 | IndexTeam/Index-Translate-9B | 108 | 9.7B | translation | — |
| 209 | MahmoodLab/UNI2-h | 107 | — | image-feature-extraction | — |
| 210 | IndexTeam/Index-Translate-2B | 98 | 2.3B | translation | — |
| 211 | black-forest-labs/flux-3-action-so101 FR | 89 | 6.9B | robotics | ✓ |
| 212 | Ultralytics/YOLO26 FR | 74 | — | object-detection | ✓ |
| 213 | jeff-legacy/Jeff-Gemma4-E2B FR | 73 | 4.6B | zero-shot-classification | ✓ |
| 214 | black-forest-labs/flux-3-action-droid FR | 73 | 6.9B | robotics | ✓ |
| 215 | MahmoodLab/UNI | 58 | — | image-feature-extraction | — |
| 216 | mistralai/Voxtral-Small-24B-2507 FR | 51 | 24.3B | audio-text-to-text | ✓ |
| 217 | nvidia/RE-USE | 41 | 10.0MB | audio-to-audio | — |
| 218 | black-forest-labs/flux-3-action-base FR | 37 | — | robotics | ✓ |
| 219 | birlaailabs/yug | 30 | 0.3B | time-series-forecasting | — |
| 220 | stabilityai/stable-fast-3d | 29 | 1.0B | image-to-3d | — |
| 221 | nlpai-lab/RenderRank-2B | 28 | 2.1B | text-ranking | — |
| 222 | bodhan-ai/indic-ocr | 24 | — | image-to-text | — |
| 223 | stabilityai/stable-audio-open-1.0 | 22 | 1.2B | text-to-audio | — |
| 224 | interfaze-ai/interfaze-1-lite FR | 17 | — | image-text-to-image | ✓ |
| 225 | MCG-NJU/OneStreamer-4B | 14 | 4.4B | video-text-to-text | — |
| 226 | nvidia/music-flamingo-hf | 14 | 8.3B | audio-text-to-text | — |
| 227 | desert-ant-labs/clear | 12 | — | audio-to-audio | — |
| 228 | RyeAI/ekko-pnc | 12 | 22.0MB | token-classification | — |
| 229 | LiquidAI/LFM2.5-Encoder-350M-GGUF FR | 8 | GGUF (inconnu) | fill-mask | ✓ |
| 230 | LiquidAI/LFM2.5-Encoder-230M-GGUF FR | 5 | GGUF (inconnu) | fill-mask | ✓ |
| 231 | nums-ai/ephris | 5 | — | graph-ml | — |
| 232 | nvidia/Lyra-2.0 | 4 | — | image-to-3d | — |
| 233 | heathcliff01/Kaloscope3.0-preview | 4 | — | image-classification | — |
| 234 | StanfordAIMI/stanford-deidentifier-with-radiology-reports-and-i2b2 | 2 | 2.0B | token-classification | — |
| 235 | MeteoSwiss/Varda-single-1.0 | 0 | — | graph-ml | — |
| 236 | NU-World-Model-Embodied-AI/phyjudge-9B | 0 | 9.0B | video-text-to-text | — |
| 237 | niclasclassen/robustness-of-transferability-estimation-metrics-for-medical-imaging | 0 | — | image-classification | — |
| 238 | nvidia/PixelUMM | 0 | — | image-to-text | — |
| 239 | becausereasons/yue2-grvl-raspy-rock-soul | 0 | — | text-to-audio | — |
| 240 | TencentARC/Pixal3D | 0 | — | image-to-3d | — |
| 241 | marcelosantoskuw/paper_015153151_visual_question_answering | 0 | — | visual-question-answering | — |
| 242 | christianhof/paper_015561242_visual_question_answering | 0 | — | visual-question-answering | — |
| 243 | huawei-bayerlab/marigold-v2-0 | 0 | — | depth-estimation | — |
| 244 | nvidia/c-fast-foundationstereo | 0 | — | depth-estimation | — |
| 245 | spellbrush/kyaraembed | 0 | — | audio-classification | — |