Browsing: Muse Glimmer

Eight months after abandoning open source over the Llama 4 benchmark scandal, Meta released Muse Glimmer, a 30 billion parameter Apache 2.0 model that runs on a single consumer GPU. Here is what it does well, where Qwen still beats it, and why Meta opened the small model instead of the big one.

Meta open-sourced Muse Glimmer, a 30-billion-parameter agentic model that runs entirely on a single consumer GPU. Here is how it works, how it benchmarks against Gemma and Qwen, and why it matters.