Llama 4 Behemoth
Meta's flagship multimodal model (RESEARCH PREVIEW ONLY - weights not publicly released)
Llama 4 Behemoth
Meta • April 2025
Training Data
Up to August 2024
Llama 4 Behemoth
April 2025
Parameters
~2 trillion (288B active)
Training Method
Mixture of Experts
Context Window
1,000,000 tokens
Knowledge Cutoff
August 2024
Key Features
Research Preview • Massive MoE Architecture • Multimodal • Not Publicly Released
Capabilities
Reasoning: Outstanding
STEM: Outstanding
Complex Tasks: Outstanding
What's New in This Version
Massive MoE model with 16 experts - announced April 2025, weights not yet publicly available
Meta's flagship multimodal model (RESEARCH PREVIEW ONLY - weights not publicly released)
What's New in This Version
Massive MoE model with 16 experts - announced April 2025, weights not yet publicly available
Technical Specifications
Key Features
Capabilities
Other Meta Models
Explore more models from Meta
Muse Spark Open
Meta's open-weight frontier model — an 816B mixture-of-experts with 42B active, natively multimodal, built for coding and long-horizon agents, and able to run on two Mac Studios
Muse Wonder
Meta's first frontier-class model, closed-weight and built for personal and professional agents, with Active Memory across conversations and Active Focus on long goals; its larger sibling, Muse Wonder Full, is reserved for paid Muse Code subscribers
Muse Spark 1.3
Meta's most capable Muse model, built for long-horizon agentic work — it collaborates, asks before consequential actions, and holds complex instructions across multi-step tasks
