Meta 开源 Muse Glimmer：30B 稠密模型，支持 120K+ 上下文与本地智能体
Run Local Agentic AI Workflows with Meta’s Muse Glimmer on NVIDIA
Meta 发布开源权重模型 Muse Glimmer，为 30B 稠密模型，上下文窗口超过 120K，面向本地 AI 智能体工作流。该模型针对 NVIDIA 边缘、桌面和工作站 AI 平台优化，在单张 GPU 上可达 20K tokens/sec，使常驻智能体能在本地处理数据。原文来自 NVIDIA 开发者博客。
Meta 开源 30B 稠密模型并给出单卡 20K tokens/sec 的本地智能体运行数据，可据此判断端侧部署门槛。
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