Meta released Muse Glimmer, a 30B parameter dense model with a 120K+ context window, designed for local, long-running agentic AI work and optimized to run on a range of NVIDIA platforms.
The dense architecture activates every parameter per token, providing high reliability, long-context coherence, and predictable latency for complex, multi-step workflows, and avoids the routing overhead seen in mixture-of-experts models.
Muse Glimmer can run fully on-device across NVIDIA GPUsincluding GeForce RTX 5090, DGX Spark, DGX Station, and Jetsonenabling private, efficient inference for use cases like software automation and autonomous agents, with flexible deployment options using NVIDIA NIM containers, SGLang, and vLLM.
AI-generated content may summarize information incompletely. Verify important information. Learn more
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic work.
Optimized to run across a range of NVIDIA edge, desktop, and workstation AI platforms, Muse Glimmer delivers 20K tokens/sec on a single GPU, enabling always-on agents to process data locally and execute complex, multi-step workflows.
Built for long-running agents, not just conversations
Most LLMs are optimized for chat , prioritizing single-turn interactions and fast time to first token—but agentic workloads demand a different approach. An agent scaffolding a software project, revising documentation, or managing a knowledge base may execute several sequential tool calls in a single session, while requiring a level of reliability, consistency, long-context coherence, and sustained throughput that chat-first models aren’t built for.