Llama 4 Scout 17B 16E Instruct

Llama 4 Scout is a powerful 17B parameter model with 16 experts, designed for efficient instruction-following tasks. With a large 131,072 token context window, it delivers high-speed performance of approximately 460 tokens per second, making it well-suited for a variety of text-based applications.

Supports a 131,072 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.