Summary
The natively multimodal mixture-of-experts model has 816 billion total parameters, 42 billion active parameters and a one-million-token context window. Meta positions it for coding, long-horizon agentic work and multimodal reasoning, with weights available through major model hubs and inference providers.
Why it matters
This materially expands access to frontier-scale open-weight models and demonstrates a practical path to running very large models locally through unified-memory systems.