Meta · Model release
Muse Glimmer 30B: Apache-2.0 local agent weights
Muse Glimmer 30B is Meta’s open-weight multimodal distill of Muse Spark for local ~24–32GB-class hardware. Meta publishes no hosted per-token list for Glimmer.
What changed
- Apache 2.0 weights announced 2026-08-10.
- This is not Muse Spark API pricing — hosted inference is billed by the serving provider.
- Official GGUF / 4-bit packs are the practical local path.
Best fit
- Local agents
- On-device coding + tool use
- Privacy-sensitive multimodal work
What to be careful about
- Full BF16 needs far more than 24GB.
- Agentic quality is not Muse Spark API quality.
Dataset snapshot: Muse Glimmer 30B is also represented in the checked comparison dataset. Prices and benchmark figures carry their own field dates.