← Model library
textvision
Llama 3.2 Vision 11B
Meta · Family Llama
Llama 3.2 Vision 11B is a lightweight multimodal model for visual QA, document reading and image content analysis. Runs interactively on a single RTX 4090.
Key Features
- ✓ Visual question answering
- ✓ Document and diagram understanding
- ✓ Low latency on a single GPU
Use Cases
- → Invoice and document extraction
- → Visual content moderation
- → Screenshot analysis