OmniLMM-12B
- Task
- Visual question answering
- Category
- Multimodal
- License
- Not stated
- Commercial use
- Check the license
The license isn't a standard one; read the model card on Hugging Face before using it commercially. - Size
- About 12 billion parameters
- Memory to load
- ~29 GB (estimate)
- Format
- FP16
- Runs on
- GPU
- Access
- Open download
- Downloads (last 30 days)
- 187
- Likes
- 74
- Last updated
- April 16, 2024
How to run it
These are full-precision weights, usually loaded with Hugging Face Transformers or Diffusers on a GPU.
Plan for roughly 29 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
In the cloud
Needs about 29 GB: use a 48 GB GPU such as an RTX A6000 or L40S.
- RunPod · rent a GPU by the hour (affiliate link)
Related visual question answering models
Data from Hugging Face's public API, last checked November 3, 2026. Downloads are Hugging Face's count for the last 30 days.