Llama-4-Scout-17B-16E-Instruct | NVIDIA NeMo AutoModel

Llama 4 is Meta’s first natively multimodal model family. Llama 4 Scout and Maverick are MoE models supporting interleaved image and text inputs.

Use this page as a checkpoint and architecture reference. Set up NeMo AutoModel with the latest container or follow the installation instructions.

Model Reference

Property	Value
Task	Image-Text-to-Text
Architecture	`Llama4ForConditionalGeneration`
Parameters	17B active (MoE)
Hugging Face Organization	meta-llama

Model	HF ID
Llama-4-Scout-17B-16E-Instruct	`meta-llama/Llama-4-Scout-17B-16E-Instruct`