# Meta releases Muse Glimmer, an open-weight 30B local agent model

Weights are available under Apache 2.0; the quantized model runs entirely on consumer hardware like a Mac or PCs with performant GPUs.

- Quantized to under 20GB and paired with a lightweight DFlash drafter model to keep token generation fast enough for real-time agent interaction on-device.
- Completes multi-step agentic tasks from a single natural-language prompt; the demo shows it discovering a local Home Assistant instance, writing an HTML/CSS/JS dashboard, and deploying a verification server.
- Claims strong performance on agentic benchmarks versus leading models in its size category.
- Weights are downloadable on Hugging Face (meta-models), with a technical blog and developer resources linked.

## Why it matters

Developers can now run a 30B agentic model entirely on consumer hardware under a permissive license, enabling private, always-on agent workflows without cloud dependency.

## Sources

- [Meta AI: Meta releases Muse Glimmer, an open-weight 30B local agent model](https://x.com/AIatMeta/status/2086757844544811485)

---

Summarized by dstilled on 2026-08-10. https://dstilled.ai/story/957eae40-86e7-486d-80e8-e3fef138c75d