Task
Image Text To Text
E
LGAI-EXAONE/EXAONE-4.5-33B
Image Text To Text·LGAI-EXAONE· 247.0K· 176
We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality. EXAONE 4.5 features 33 billion parameters in total, including 1.2 billion parameters from the vision encoder. EXAONE 4.5 achieves competitive performance in general be
# pull & run locally
pip install mlforge-sdk && mlforge pull LGAI-EXAONE/EXAONE-4.5-33B
pip install mlforge-sdk && mlforge pull LGAI-EXAONE/EXAONE-4.5-33B
Model details
Provider
LGAI-EXAONE
Framework
transformers
Parameters
34.4B
Size
64 GB
License
other
Downloads
247.0K
Likes
176
Paper
arXiv:2604.08644
Updated
2026-06-16
About LGAI-EXAONE/EXAONE-4.5-33B
We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality. EXAONE 4.5 features 33 billion parameters in total, including 1.2 billion parameters from the vision encoder. EXAONE 4.5 achieves competitive performance in general benchmark while outperforming SOTA models of similar size in document understanding and Korean contextual reasoning, inheriting powerful language capabilities from our previous language models.