Meta introduces Muse Glimmer, a 30-billion-parameter agentic model released under the Apache 2.0 license, optimized for always-on local agent workflows on a device like a Mac or PC with a single consumer GPU.

Meta introduces Muse Glimmer, a 30-billion-parameter agentic model released under the Apache 2.0 license, optimized for always-on local agent workflows on a device like a Mac or PC with a single consumer GPU.

Meta releases open-weight multimodal MoE model with 816B parameters
Meta released Muse Glimmer, a 30B parameter multimodal model distilled from Muse, licensed under Apache 2.0, designed for local agentic use cases like coding, document analysis, and personal assistants. It includes a 2B vision encoder and a 28B text decoder with hybrid attention and Gated Grouped-Query Attention. Support for transformers, llama.cpp, vLLM, and Inference Endpoints is provided day-0. Benchmarks show competitive performance in agentic and multimodal tasks against models like Gemma4-31B and Qwen3.6-27B.
muse-glimmer · 1,425 (1,415–1,434) · 3,897 votes
Muse Glimmer · 1,425 · $0.53 per 1M tokens
Muse Glimmer · 1,425 · $0.53 per 1M tokens
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 20 October 2026 · Artificial Analysis, read 20 October 2026