Meta Introduces Muse Ember, Smallest and Most Efficient Model for Agent Work

Meta introduced Muse Ember, its smallest and most efficient model, built for complex reasoning execution and everyday agent work. The model can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes, and features a 1M-token context window with native understanding of text, images, audio and video.
Event version 1.
Key insights
Smallest and most efficient model
Muse Ember is described as Meta's smallest and most efficient model. It is built for complex reasoning execution and everyday agent work.
Agent workflow capabilities
Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes.
1M-token context and multimodal input
The model has a 1M-token context window and native understanding of text, images, audio and video. It can work across large document sets and varied inputs.