Hugging Face Blog·· 21 hours agoFeaturedAI Score88
Meta releases Muse Spark Open, an open-weight 816B-parameter multimodal MoE model
Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
AI summary
Meta released Muse Spark Open, an open-weight mixture-of-experts model with roughly 816B total parameters and about 42B active per token.
Why it matters
The post gives the architecture, deployment recipes and fine-tuning numbers, so readers can judge what running an 816B open-weight MoE actually costs.
Source: Hugging Face Blog · huggingface.co