BETA
Smaller Llama 3.2 vision model — fits on a single GPU while keeping multimodal capability.
Llama 3.2 11B Vision is a multimodal AI model from Meta. It costs $0.160 per million input tokens and $0.160 per million output tokens (blended $0.160/M), with a 128K-token context window.
Llama 3.2 11B Vision costs $0.160 per million input tokens and $0.160 per million output tokens, for a blended reference rate of $0.160 per million tokens.
Llama 3.2 11B Vision supports up to 128K tokens of context (128,000 tokens).
Llama 3.2 11B Vision is well suited to Single-GPU vision, Open weights and Cheap multimodal.
Llama 3.2 11B Vision is developed and served by Meta. It was released in Sep 2024.