Llama 4 Scout 17B Instruct

Llama 4 Scout 17B Instruct is the cataloged Instruct identity for Meta’s open Scout weights. As with Maverick, 17B describes active rather than all MoE parameters. Its defining property is a context window of about ten million tokens for text and images.

The weights use the Llama 4 Community License. Llama 4 Scout leads to the family checkpoint, while Llama 4 Maverick 17B Instruct is the Maverick variant with a smaller context window. For Scout, the model card lists vLLM and SGLang, along with quantizations for llama.cpp, Ollama, and LM Studio.