Meta 发布 Muse Glimmer：开源多模态模型，支持图像视频与工具调用
原标题：llmsvlmsmeta Meta is back with Muse Glimmer: local, agentic, multimodal, and open source 2 August 10, 2026
AI 摘要
Meta 发布了 Muse Glimmer，一个 30B 参数的开源多模态模型，包含 2B 视觉编码器和 28B 文本解码器，支持图像、视频和工具调用。该模型在 transformers、llama.cpp、vLLM 等库中获得首发支持，并采用混合注意力、门控分组查询注意力等架构优化。Muse Glimmer 还提供了可选的投机解码模块，以加速生成。
正文节选
To celebrate, we are shipping with Meta day-0 support in transformers, llama.cpp, vLLM, Inference Endpoints, and other libraries. We built a few cool things and explain our findings in this blog. Check out the demos below for inspiration. You can find all Muse Glimmer models in this collection. Muse Glimmer is a dense 30B parameter model consisting of: - 2B ViT-style encoder for vision (Perception Encoder) - 28B parameter text decoder In addition to the main VLM, there’s also a speculative decod