{"id":"2d23b7ff-25c8-46b7-bd3a-52eac66e7da8","slug":"hf-model-redhatai-molmo2-4b-kdiltt-i","name":"Molmo2-4B","description":"Hugging Face model RedHatAI/Molmo2-4B. Task: image text to text. Library: transformers. 51 downloads.","capabilities":["transformers","safetensors","molmo2","image-text-to-text","multimodal","olmo","molmo","conversational","custom_code","en","dataset:allenai/Molmo2-Cap","dataset:allenai/Molmo2-VideoCapQA","dataset:allenai/Molmo2-VideoSubtitleQA","dataset:allenai/Molmo2-AskModelAnything","dataset:allenai/Molmo2-VideoPoint","dataset:allenai/Molmo2-VideoTrack","dataset:allenai/Molmo2-MultiImageQA","dataset:allenai/Molmo2-SynMultiImageQA","dataset:allenai/Molmo2-MultiImagePoint","base_model:Qwen/Qwen3-4B-Instruct-2507"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:08.617Z"}