Thrilled to bring Meta’s Llama 4 Scout and Maverick to Foundry today, as we continue to make Azure the platform of choice for the world’s most advanced AI models.
Meta’s🦙Llama 4 herd is starting to roll out now on Azure AI Foundry! I’m really excited about these models because they seamlessly integrate text and vision tokens, setting a new standard for agentic applications. What impresses me most about Llama 4 Scout is its ability to fit in a single H100 GPU while supporting near infinite 10m token context window. This will be great for tasks like multi-document summarization and reasoning over vast codebases. Llama 4 Maverick, with 17b active parameters, excels in image and text understanding with support for 12 languages. I think it’s ideal for creating sophisticated apps that bridge language barriers or interactive scenarios like customer support. See more here on #Llama 4 on Microsoft Azure https://lnkd.in/g_nt766N Huge thanks to Connor Hayes, the Meta team, and our AI Platform team members.
