Suivi des modeles HuggingFace vs deploiements internes InfoCEPO
Mis a jour : 2026-06-09 07:55 UTC | Source : HuggingFace Trending
| Status | Modele | Categorie | Telechargements | Date | Endpoint InfoCEPO |
|---|---|---|---|---|---|
| 🟢 | Qwen/Qwen3-VL-8B-Instruct | Vision-Language (VLM) | 8.2M | 2025-10-11 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - Variante VLM (vision-language) |
| 🟢 | openai/whisper-large-v3-turbo | Speech Recognition (STT) | 7.9M | 2024-10-01 | | ai-stt - Transcription vocale multilingue (OpenAI) |
| 🟢 | Qwen/Qwen3.6-27B-FP8 | Vision-Language (VLM) | 7.2M | 2026-04-21 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - 4 variantes: nothink, tool-use, thinking, vision |
| 🟢 | Qwen/Qwen3.6-35B-A3B | Vision-Language (VLM) | 5.8M | 2026-04-15 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - 4 variantes: nothink, tool-use, thinking, vision |
| 🟢 | Qwen/Qwen3.6-27B | Vision-Language (VLM) | 5.6M | 2026-04-21 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - 4 variantes: nothink, tool-use, thinking, vision |
| 🟢 | Qwen/Qwen3.6-35B-A3B-FP8 | Vision-Language (VLM) | 5.5M | 2026-04-15 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - 4 variantes: nothink, tool-use, thinking, vision |
| 🟢 | openai/whisper-large-v3 | Speech Recognition (STT) | 5.1M | 2023-11-07 | | ai-stt - Transcription vocale multilingue (OpenAI) |
| 🟢 | Qwen/Qwen3-VL-4B-Instruct | Vision-Language (VLM) | 4.0M | 2025-10-11 | | ai-multilingual / ai-tools / ai-thinking / ai-vision - Variante VLM (vision-language) |
| Status | Modele | Priorite | Telechargements | Likes | Date | Categories |
|---|---|---|---|---|---|---|
| 🔵 | cross-encoder/ms-marco-MiniLM-L6-v2 | A evaluer Haute | 70.2M | 260 ♥ | 2022-03-02 | text-ranking |
| 🔵 | google-bert/bert-base-uncased | A evaluer Haute | 58.4M | 2678 ♥ | 2022-03-02 | fill-mask |
| 🔵 | BAAI/bge-small-en-v1.5 | A evaluer Haute | 53.2M | 483 ♥ | 2023-09-12 | feature-extraction |
| 🔵 | BAAI/bge-m3 | A evaluer Haute | 29.2M | 3096 ♥ | 2024-01-27 | sentence-similarity |
| 🔵 | Qwen/Qwen3-0.6B | A evaluer Haute | 22.8M | 1308 ♥ | 2025-04-27 | Large Language Model |
| 🔵 | laion/clap-htsat-fused | A evaluer Haute | 19.2M | 103 ♥ | 2023-02-16 | audio-classification |
| 🔵 | Qwen/Qwen3-4B | A evaluer Haute | 17.7M | 630 ♥ | 2025-04-27 | Large Language Model |
| 🔵 | colbert-ir/colbertv2.0 | A evaluer Haute | 16.3M | 357 ♥ | 2023-06-27 | Other |
| 🔵 | autogluon/chronos-2 | A evaluer Haute | 14.2M | 32 ♥ | 2025-10-06 | time-series-forecasting |
| 🔵 | BAAI/bge-large-en-v1.5 | A evaluer Haute | 14.2M | 683 ♥ | 2023-09-12 | feature-extraction |
| 🔵 | hexgrad/Kokoro-82M | A evaluer Haute | 14.1M | 6289 ♥ | 2024-12-26 | Text-to-Speech (TTS) |
| 🔵 | BAAI/bge-reranker-v2-m3 | A evaluer Haute | 14.0M | 1027 ♥ | 2024-03-15 | text-classification |
| 🔵 | openai-community/gpt2 | A evaluer Haute | 13.7M | 3293 ♥ | 2022-03-02 | text-generation |
| 🔵 | amazon/chronos-2 | A evaluer Haute | 13.6M | 316 ♥ | 2025-10-30 | time-series-forecasting |
| 🔵 | Qwen/Qwen2.5-3B-Instruct | A evaluer Haute | 13.4M | 492 ♥ | 2024-09-17 | Large Language Model |
| 🔵 | Bingsu/adetailer | A evaluer Haute | 12.8M | 719 ♥ | 2023-04-26 | Other |
| 🔵 | google/gemma-4-26B-A4B-it | A evaluer Haute | 12.3M | 1103 ♥ | 2026-03-11 | Vision-Language (VLM) |
| 🔵 | Qwen/Qwen2.5-7B-Instruct | A evaluer Haute | 11.9M | 1341 ♥ | 2024-09-16 | Large Language Model |
| 🔵 | Qwen/Qwen3-8B | A evaluer Haute | 11.9M | 1127 ♥ | 2025-04-27 | Large Language Model |
| 🔵 | google/gemma-4-31B-it | A evaluer Haute | 11.1M | 2942 ♥ | 2026-03-11 | Vision-Language (VLM) |
| 🔵 | Qwen/Qwen2.5-1.5B-Instruct | A evaluer Haute | 10.6M | 733 ♥ | 2024-09-17 | Large Language Model |
| 🔵 | facebook/opt-125m | A evaluer Haute | 10.5M | 264 ♥ | 2022-05-11 | text-generation |
| 🔵 | autogluon/chronos-bolt-small | A evaluer Haute | 10.1M | 43 ♥ | 2024-11-13 | time-series-forecasting |
| 🔵 | meta-llama/Llama-3.1-8B-Instruct | A evaluer Haute | 10.0M | 6021 ♥ | 2024-07-18 | Large Language Model |
| 🔵 | Qwen/Qwen3.5-4B | A evaluer Haute | 9.8M | 618 ♥ | 2026-02-27 | Vision-Language (VLM) |
| 🔵 | Qwen/Qwen3.5-9B | A evaluer Haute | 9.5M | 1538 ♥ | 2026-02-27 | Vision-Language (VLM) |
| 🔵 | coqui/XTTS-v2 | A evaluer Haute | 9.0M | 3586 ♥ | 2023-10-31 | Text-to-Speech (TTS) |
| 🔵 | lpiccinelli/unidepth-v2-vitl14 | A evaluer Haute | 8.9M | 32 ♥ | 2024-06-12 | Computer Vision |
| 🔵 | argmaxinc/whisperkit-coreml | A evaluer Haute | 8.6M | 189 ♥ | 2024-02-28 | Speech Recognition (STT) |
| 🔵 | BAAI/bge-base-en-v1.5 | A evaluer Haute | 8.6M | 436 ♥ | 2023-09-11 | feature-extraction |
| 🔵 | intfloat/multilingual-e5-small | A evaluer Haute | 8.4M | 335 ♥ | 2023-06-30 | sentence-similarity |
| 🔵 | pyannote/speaker-diarization-3.1 | A evaluer Haute | 8.4M | 2217 ♥ | 2023-11-16 | automatic-speech-recognition |
| 🔵 | google/gemma-3-270m | A evaluer Haute | 8.1M | 1032 ♥ | 2025-08-05 | Large Language Model |
| 🔵 | Falconsai/nsfw_image_detection | A evaluer Haute | 8.1M | 1093 ♥ | 2023-10-13 | Computer Vision |
| 🔵 | pyannote/wespeaker-voxceleb-resnet34-LM | A evaluer Haute | 7.9M | 145 ♥ | 2023-11-13 | Other |
| 🔵 | meta-llama/Llama-3.2-1B-Instruct | A evaluer Haute | 7.5M | 1466 ♥ | 2024-09-18 | Large Language Model |
| 🔵 | openai/gpt-oss-20b | A evaluer Haute | 7.5M | 4693 ♥ | 2025-08-04 | text-generation |
| 🔵 | pyannote/segmentation-3.0 | A evaluer Haute | 7.2M | 1115 ♥ | 2023-09-22 | voice-activity-detection |
| 🔵 | facebook/contriever | A evaluer Haute | 7.1M | 90 ♥ | 2022-03-02 | Other |
| 🔵 | intfloat/multilingual-e5-large | A evaluer Haute | 7.0M | 1202 ♥ | 2023-06-30 | feature-extraction |
| 🔵 | ProsusAI/finbert | A evaluer Haute | 6.8M | 1175 ♥ | 2022-03-02 | text-classification |
| 🔵 | Qwen/Qwen2.5-VL-7B-Instruct | A evaluer Haute | 6.6M | 1564 ♥ | 2025-01-26 | Vision-Language (VLM) |
| 🔵 | deepseek-ai/DeepSeek-R1-0528 | A evaluer Haute | 6.5M | 2450 ♥ | 2025-05-28 | Large Language Model |
| 🔵 | google/gemma-4-E4B-it | A evaluer Haute | 6.3M | 1218 ♥ | 2026-03-02 | Large Language Model |
| 🔵 | timm/mobilenetv3_small_100.lamb_in1k | A evaluer Haute | 5.7M | 77 ♥ | 2022-12-16 | Computer Vision |
| 🔵 | deepseek-ai/DeepSeek-R1 | A evaluer Haute | 5.7M | 13379 ♥ | 2025-01-20 | Large Language Model |
| 🔵 | intfloat/multilingual-e5-base | A evaluer Haute | 5.6M | 361 ♥ | 2023-05-19 | sentence-similarity |
| 🔵 | google-bert/bert-large-uncased | A evaluer Haute | 5.6M | 147 ♥ | 2022-03-02 | fill-mask |
| 🔵 | deepseek-ai/DeepSeek-V4-Pro | A evaluer Haute | 5.4M | 4724 ♥ | 2026-04-22 | Large Language Model |
| 🔵 | Comfy-Org/Wan_2.2_ComfyUI_Repackaged | A evaluer Haute | 5.4M | 731 ♥ | 2025-07-27 | Image Generation |
| 🔵 | trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 | A evaluer Haute | 5.3M | 7 ♥ | 2024-11-25 | Large Language Model |
| 🔵 | Qwen/Qwen2.5-VL-3B-Instruct | A evaluer Haute | 5.3M | 655 ♥ | 2025-01-26 | Vision-Language (VLM) |
| 🔵 | cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit | A evaluer Haute | 5.0M | 78 ♥ | 2026-04-03 | Vision-Language (VLM) |
| 🔵 | google/vit-base-patch16-224 | A evaluer Moyenne | 4.7M | 968 ♥ | 2022-03-02 | Computer Vision |
| 🔵 | Qwen/Qwen3-4B-Instruct-2507 | A evaluer Moyenne | 4.7M | 874 ♥ | 2025-08-05 | Large Language Model |
| 🔵 | Qwen/Qwen3-1.7B | A evaluer Moyenne | 4.7M | 480 ♥ | 2025-04-27 | Large Language Model |
| 🔵 | openai/gpt-oss-120b | A evaluer Moyenne | 4.5M | 4866 ♥ | 2025-08-04 | text-generation |
| 🔵 | dphn/dolphin-2.9.1-yi-1.5-34b | A evaluer Moyenne | 4.4M | 64 ♥ | 2024-05-18 | Large Language Model |
| 🔵 | dima806/fairface_age_image_detection | A evaluer Moyenne | 4.3M | 74 ♥ | 2024-12-06 | Computer Vision |
| 🔵 | openai/whisper-base | A evaluer Moyenne | 4.3M | 271 ♥ | 2022-09-26 | Speech Recognition (STT) |
| 🔵 | zai-org/GLM-OCR | A evaluer Moyenne | 4.2M | 1817 ♥ | 2026-01-30 | Vision-Language (VLM) |
| 🔵 | hmellor/tiny-random-LlamaForCausalLM | A evaluer Moyenne | 4.1M | 0 ♥ | 2025-04-29 | Large Language Model |
| 🔵 | facebook/esm2_t33_650M_UR50D | A evaluer Moyenne | 4.1M | 80 ♥ | 2022-09-27 | fill-mask |
| 🔵 | deepseek-ai/DeepSeek-V3.2 | A evaluer Moyenne | 4.1M | 1445 ♥ | 2025-12-01 | Large Language Model |
| 🔵 | facebook/w2v-bert-2.0 | A evaluer Moyenne | 4.1M | 217 ♥ | 2023-12-19 | feature-extraction |
| 🔵 | Qwen/Qwen2.5-0.5B-Instruct | A evaluer Moyenne | 4.0M | 528 ♥ | 2024-09-16 | Large Language Model |
| 🔵 | distilbert/distilgpt2 | A evaluer Moyenne | 4.0M | 630 ♥ | 2022-03-02 | text-generation |
| 🔵 | BAAI/bge-reranker-base | A evaluer Moyenne | 3.8M | 236 ♥ | 2023-09-11 | text-classification |
| 🔵 | answerdotai/ModernBERT-base | A evaluer Moyenne | 3.8M | 1049 ♥ | 2024-12-11 | fill-mask |
| 🔵 | google-bert/bert-base-multilingual-uncased | A evaluer Moyenne | 3.8M | 157 ♥ | 2022-03-02 | fill-mask |
| 🔵 | BAAI/bge-small-zh-v1.5 | A evaluer Moyenne | 3.8M | 116 ♥ | 2023-09-12 | feature-extraction |
| 🔵 | google-bert/bert-base-cased | A evaluer Moyenne | 3.7M | 360 ♥ | 2022-03-02 | fill-mask |
| 🔵 | Qwen/Qwen2-1.5B-Instruct | A evaluer Moyenne | 3.7M | 162 ♥ | 2024-06-03 | Large Language Model |
| 🔵 | Qwen/Qwen3-32B | A evaluer Moyenne | 3.7M | 700 ♥ | 2025-04-27 | Large Language Model |
| 🔵 | mistralai/Mistral-7B-Instruct-v0.3 | A evaluer Moyenne | 3.4M | 2622 ♥ | 2024-05-22 | Large Language Model |
| 🔵 | deepseek-ai/DeepSeek-OCR | A evaluer Moyenne | 2.6M | 3274 ♥ | 2025-10-17 | Vision-Language (VLM) |
| 🔵 | moonshotai/Kimi-K2.5 | A evaluer Moyenne | 1.7M | 2814 ♥ | 2026-01-01 | Vision-Language (VLM) |
| 🔵 | mistralai/Mistral-7B-Instruct-v0.2 | A evaluer Moyenne | 1.6M | 3157 ♥ | 2023-12-11 | Large Language Model |
| 🔵 | stabilityai/stable-diffusion-xl-base-1.0 | A evaluer Moyenne | 1.4M | 7803 ♥ | 2023-07-25 | Image Generation |
| 🔵 | meta-llama/Meta-Llama-3-8B-Instruct | A evaluer Moyenne | 1.4M | 4581 ♥ | 2024-04-17 | Large Language Model |