robotflowlabs/qwen3-vl-2b-instruct-int4
Image-Text-to-Text • 2B • Updated • 16
ANIMA VLM
INT4 vision-language models for robotic scene understanding. Qwen2.5-VL for visual QA and grounding.
INT4 vision-language models for robotic scene understanding. Qwen2.5-VL for visual QA and grounding.