Meta 开源 Muse Glimmer：30B 稠密模型，面向本地智能体工作流
Run Local Agentic AI Workflows with Meta’s Muse Glimmer on NVIDIA
Meta 重返开源生态，发布 Muse Glimmer，一个 30B 开源权重稠密模型，上下文窗口超过 120K，面向本地 AI 智能体工作。该模型针对 NVIDIA 边缘、桌面和工作站 AI 平台优化，可在单 GPU 上达到 20K tokens/sec，让常驻智能体在本地处理数据并执行复杂任务。
Meta 回归开源发布 30B 本地智能体模型，并给出单 GPU 吞吐数字和运行平台范围。
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI...
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic work. Optimized to run across a range of NVIDIA edge, desktop, and workstation AI platforms, Muse Glimmer delivers 20K tokens/sec on a single GPU, enabling always-on agents to process data locally and execute complex…
来源：NVIDIA Developer Blog · developer.nvidia.com