{"id":"0abc1a49-b8ae-4598-a4c8-3fb52c85a95e","slug":"hf-model-ezcon-smolvlm2-2-2b-instruct-mlx-pjjl3d-w","name":"SmolVLM2-2.2B-Instruct-mlx","description":"Hugging Face model EZCon/SmolVLM2-2.2B-Instruct-mlx. Task: image text to text. Library: mlx. 29 downloads.","capabilities":["mlx","safetensors","smolvlm","video-text-to-text","image-text-to-text","conversational","en","dataset:HuggingFaceM4/the_cauldron","dataset:HuggingFaceM4/Docmatix","dataset:lmms-lab/LLaVA-OneVision-Data","dataset:lmms-lab/M4-Instruct-Data","dataset:HuggingFaceFV/finevideo","dataset:MAmmoTH-VL/MAmmoTH-VL-Instruct-12M","dataset:lmms-lab/LLaVA-Video-178K","dataset:orrzohar/Video-STaR","dataset:Mutonix/Vript","dataset:TIGER-Lab/VISTA-400K","dataset:Enxin/MovieChat-1K_train","dataset:ShareGPT4Video/ShareGPT4Video","base_model:HuggingFaceTB/SmolVLM2-2.2B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:48.616Z"}