Meta 发布开源权重模型 Muse Spark Open，定位为面向编码和智能体工作的模型，擅长长程任务、复杂软件工程和多步推理。模型总参数 816B、激活 42B，上下文窗口 1M token，原生支持文本、图像、视频、音频多模态。NVIDIA 透露该模型在 GB300 NVL72 上训练，并针对 Blackwell Ultra 提供 NVFP4 量化 checkpoint，吞吐超过 50K tokens/sec/GPU；NVFP4 版本已上架 Hugging Face。
同一新闻，精选展示《Meta 发布开源权重多模态 MoE 模型 Muse Spark Open：816B 参数、1M 上下文》
And @AIatMeta went live with Muse Spark Open!
The 816B model was trained on NVIDIA GB300 NVL72. Its 1M-token context window gives coding agents room to work across large codebases.
Meta also produced NVFP4 checkpoints optimized for Blackwell Ultra, delivering over 50K tokens/sec/GPU to improve throughput and lower cost per token.
Congrats to the @Muse team.
More in our blog: https://nvda.ws/4B8d9g4
NVFP4: https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B-NVFP4
Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token context window → Natively multimodal across text, image, video, audio在 X 查看被引用的帖子
来源：NVIDIA AI · x.com