Meta 发布开源模型 Muse Spark Open：816B 参数、1M 上下文
Meta 放出了 816B 的开源模型 Muse Spark Open，主打编程和智能体，上下文有 1M token，还给了 NVFP4 权重，做代码库级任务可以看看。
Meta 发布开源权重模型 Muse Spark Open，总参数 816B、激活 42B，定位编程与智能体任务。模型上下文窗口达 1M token，支持跨大型代码库的长任务软件工程，并原生覆盖文本、图像、视频、音频四种模态。该模型在 NVIDIA GB300 NVL72 上训练，Meta 还针对 Blackwell Ultra 提供 NVFP4 量化权重，单卡吞吐超过 50K tokens/sec 以降低推理成本。Meta 称其为目前能力最强的美国开源权重模型。
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: nvda.ws/4B8d9g4 NVFP4: huggingface.co/meta-models/Mu… AI at Meta @AIatMeta 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 🔗 View Quoted Tweet 💬 3 🔄 1 ❤️ 16 👀 1341 📊 4 ⚡
