Meta 把 30B 多模态模型开源了，Apache 2.0，还能跑在本地，vLLM 当天就支持，想试的直接装。
Meta 旗下 Superintelligence Labs 发布首个开源权重模型 Muse Glimmer 30B，采用 Apache 2.0 许可。该模型为 30B 稠密架构，支持 128K 以上上下文，具备多模态能力，面向本地智能体场景。vLLM 在发布当天即提供 Day-0 支持，用户可通过命令 vllm serve meta-models/Muse-Glimmer-30B 在自有设备上运行。官方称其既能应对长周期任务，又可在用户自持硬件上运行。
@AIatMeta https://t.co/VPWL6oRtBq
@AIatMeta x.com/vllm_project/s… vLLM @vllm_project @Meta is back in open source. Excited to announce Day-0 vLLM support for Muse Glimmer 30B, the first open-weights model from Meta Superintelligence Labs — which ships under Apache 2.0!!! 30B dense, 128K+ context, multimodal, built for local agents. Capable enough for long-horizon tasks, small enough to run on hardware you own. Try it now on your device: vllm serve meta-models/Muse-Glimmer-30B Kudos to @inferact , @AIatMeta , and @NVIDIAAI for bringing the model alive in vLLM! 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 1 👀 179 ⚡