LLaDA-V

GSAI-ML/LLaDA-V

Image Text to Text8.4B parameterstransformers
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
14.5K
Total downloads
122.9K
Gained 7D
+1,378(increase)
1.2%(up) vs baseline
Gained 30D
—
Likes
28
+0 in 7D
Rank · tracked models
#6,795
20(down 20 places)this week
Parameters
8.4B
Last source update
Mar 23, 2026
Momentum
55.7
  • LLaDA-V gained 1,378 downloads during the last seven tracked days.
  • It moved from #836 to #837 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

LLaDA-V is a image text to text model published by GSAI-ML. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 5, 2026.

Published
May 28, 2025
Last updated
Mar 23, 2026
Library
transformers
License
—
Task
Image Text to Text
Parameters
8,433,894,944
Spaces
—
Derivative models
—
Velocity 7D/day
197
transformerssafetensorsllava_lladaimage-text-to-textconversationalcustom_codearxiv:2603.01068arxiv:2505.16933endpoints_compatibleregion:us

Similar models

Models similar to LLaDA-V
ModelDL 30D
Idefics3-8B-Llama3HuggingFaceM4124.7K
idefics2-8bHuggingFaceM475.9K
idefics2-8b-chattyHuggingFaceM4333
idefics2-8b-baseHuggingFaceM41,385
Ferret-UI-Llama8bjadechoghari145
llama-joycaption-beta-one-hf-llavafancyfeast114.8K
GSAI-ML/LLaDA-V — Downloads, Growth & Stats | OpenModelStats