Llama 3.2 Vision
Meta Llama 3.2 Vision on Ollama for image reasoning. The default library tag is the 11B variant, about 7.8 GB, with a 128K context window.
Type: local
Context: 131,072 tokens
Use cases: vision, general
Limits checked against official docs on 2026-10-10. Rates change without notice. Not affiliated with providers unless noted. Verify before production use.