SmolVLM2
Smallest Video LM Ever from HuggingFace. SmolVLM2, from HuggingFace, is a series of tiny, open-source multimodal model for video understanding.
Reactions (1)
Similar products
by description similarity
Marlin-2B
huggingface.coa tiny VLM to extract structured information from videos
SmolVLA
huggingface.coPowerful robotics VLA that runs on consumer hardware
SmolDocling
huggingface.co256M VLM for end-to-end document AI
Molmo 2
allenai.orgSOTA video understanding, pointing, and tracking VLM
MiniCPM-V 4.6
github.comUltra-efficient 1.3B vision-language model for mobile