Meta Muse Glimmer: The 30B Open Agent Model That Runs on Your Own GPU

Meta has open-sourced Muse Glimmer, a 30-billion-parameter model for autonomous agent workflows, available under Apache 2.0 on Hugging Face and Ollama. Distilled from Meta's larger Muse Spark system, it focuses on tool calling, multi-step task execution, and failure recovery, with a Q4 quantized version of about 20 GB designed to run on local hardware.

Meta just open-sourced Muse Glimmer — a 30-billion-parameter model built specifically for autonomous agent workflows, and it runs entirely on your own hardware. Apache 2.0 license. Available on Hugging Face and Ollama right now. This is not a general-purpose chat model with “agentic features” taped on afterward. It was distilled from Meta’s larger Muse Spark system with one goal: tool calling, multi-step task execution, and failure recovery at the local inference layer. One Command Away The fastest path to running Muse Glimmer is Ollama: Quantized to Q4, the model sits at roughly 20 GB — designed to fit on a … The post