LLaVA-OneVision-2-8B-Instruct

lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct

Image Text to Text8.5B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
Downloads 30D
8,763
Total downloads
194K
Gained 7D
+2,711(increase)
1.4%(up) vs baseline
Gained 30D
—
Likes
15
+0 in 7D
Rank · tracked models
#8,764
364(up 364 places)this week
Parameters
8.5B
Last source update
Aug 30, 2026
Momentum
59.5
  • LLaVA-OneVision-2-8B-Instruct gained 2,711 downloads during the last seven tracked days.
  • It moved from #1049 to #1025 among tracked Image Text to Text models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

LLaVA-OneVision-2-8B-Instruct is a image text to text model published by lmms-lab-encoder. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 7, 2026.

Published
May 11, 2026
Last updated
Aug 30, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
8,527,213,568
Spaces
—
Derivative models
—
Velocity 7D/day
387
transformerssafetensorsllava_onevision2image-text-to-textmultimodalvision-languagevideo-text-to-textllavallava-onevision-2qwen3conversationalcustom_code

Similar models

Models similar to LLaVA-OneVision-2-8B-Instruct
ModelDL 30D
LLaVA-OneVision-1.5-8B-Instructlmms-lab10.9K
Sa2VA-Qwen2_5-VL-7BByteDance443
InternVL3_5-8BOpenGVLab40.6K
InternVL3_5-8B-HFOpenGVLab30K
InternVL3_5-8B-InstructOpenGVLab2,695
CapRL-InternVL3.5-8Binternlm402
lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct — Downloads, Growth & Stats | OpenModelStats