Overview
A natively multimodal MoE with 17B active parameters, 16 experts, and up to 10M context.
A natively multimodal MoE with 17B active parameters, 16 experts, and up to 10M context.
Only published specifications are shown.
A natively multimodal MoE with 17B active parameters, 16 experts, and up to 10M context.
Llama 4 Scout launched as an open multimodal MoE.
View sourceSelect a card to view the related model.