Muse Glimmer 30B

Name: Muse Glimmer 30B
Author: Meta

Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access.

Model page

View on OpenRouter

Specs

Model

Family: Muse
Variant: Glimmer 30B
Parameters: 29.6B
Weights: Open
License: Apache-2.0

Limits

Context: 131,072 tokens

Modalities

Input: Text Image
Output: Text

Capabilities

Reasoning: Yes
Reasoning control: Effort levels
Tool calling: Yes
Attachments: Yes

Dates

Announced: 10 Aug 2026
Released: 10 Aug 2026
Knowledge cutoff: 4 Jan 2026

Articles

All articles

10 Aug 2026

Meta AI Research

Introducing Muse Glimmer: An Open Agentic Model That Runs on Your Device

Muse Glimmer is a 30-billion-parameter open agentic model from Meta Superintelligence Labs, optimized for always-on local workflows on consumer hardware.

Meta Superintelligence Labs

research.meta.ai