12
SpaceThinker-Qwen2.5VL-3B
🌌
Answer questions using images and text
SpaceVLMs
Features VLMs fine-tuned for enhanced spatial reasoning using a synthetic data pipeline similar to Spatial VLM.
-
-
2
SpaceQwen2.5 VL 3B Instruct
👑 -
remyxai/SpaceLLaVA
Image-Text-to-Text • 13B • Updated • 341 • 24 -
remyxai/SpaceQwen2.5-VL-3B-Instruct
Image-Text-to-Text • 4B • Updated • 10.9k • 15 -
remyxai/SpaceMantis
Image-to-Text • 8B • Updated • 10 • 1 -
remyxai/SpaceFlorence-2
0.3B • Updated • 90 • 2 -
remyxai/SpaceMinitron-4B
Updated • 4 • 1 -
remyxai/SpaceLlama3.1
Updated • 9 • 8 -
remyxai/SpaceLLaVA-NeXT
8B • Updated • 3 -
remyxai/SpaceLLaVA-lite
Updated • 15 • 3 -
remyxai/SpaceLlama3.1-hf
Image-to-Text • 9B • Updated • 3 • 2