Urgent.News

What's breaking now, across thousands of outlets.

AI

Llama 4 Scout: What Meta's open-weight multimodal brings to product teams

Originally published on juliancardozo.github.io. Llama 4 Scout is Meta's open-weight multimodal model that is worth looking at when evaluating vision, text, and long context capabilities under a proprietary deployment strategy. Its proposal combines a Mixture-of-Experts architecture, 17 billion parameters activated by inference, and a declared context window of up to 10 million…

Translated from Spanish Read in Spanish

Meta has introduced Llama 4 Scout, a multimodal model that combines text, vision, and long context capabilities. The model features 109 billion total parameters, with 17 billion activated during inference, and a context window of up to 10 million tokens. Llama 4 Scout uses a Mixture-of-Experts architecture with 16 experts, allowing for increased capacity without executing all parameters for each token.

The model is available under the Llama 4 Community License, which has specific conditions for use, including restrictions for organizations with over 700 million monthly active users.

Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

More from Tuesday 17 November →