Meta launches Muse Spark Open, a coding-focused mixture-of-experts model with 816B total parameters, 42B active, and a 1M-token context window. NVIDIA's developer blog covers scaling agentic coding workflows with it on GB300 NVL72 systems.

Meta launches Muse Spark Open, a coding-optimized 816B mixture-of-experts (MoE) model with 42B active parameters and a 1M token context window. Trained on...