Meta open-sourced muse glimmer, a 30 billion parameter model built for always-on local agents that…
meta open-sourced muse glimmer, a 30 billion parameter model built for always-on local agents that runs on a single gpu or a mac and ships with persistent state and self-managed memory. it is tuned for tool use, long tasks, and failure recovery, licensed apache 2.0.
the always-on agent is becoming a laptop process, not a cloud bill.
Context
Meta Research's post of 10 August 2026 introduces Muse Glimmer, a 30-billion-parameter model optimized for always-on local agent workflows, and open sources the weights under Apache 2.0. It says the model is small enough to run on a Mac or PC with a single consumer GPU, with weights on Hugging Face, about 4-bit quantization with the language model under 20 GB, and a drafter for speculative decoding. The Hugging Face page lists Meta Superintelligence Lab as author, an August 2026 release and Apache 2.0.
The release is dated 10 August 2026, about six weeks before the note. Persistent state and self-managed memory were not found as shipped features in the text read; the blog lists long-context memory as a needed capability. The benchmark comparison against Gemma4 31B and Qwen3.6 27B was seen as an image table only and is vendor-reported. The line that the always-on agent is becoming a laptop process is the author's opinion.
Watch next
- Independent local-agent evaluations.
Sources
- Introducing Muse Glimmer (Meta Research, 10 Aug 2026)research.meta.ai
- Muse-Glimmer-30B (Hugging Face)huggingface.co
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 19 September 2026 at 00:41 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →