Llama 4 Maverick is a high-capacity multimodal language model from Meta, built on a MoE architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Supports & produces multilingual text and image input, and code output across 12 languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.