Introducing Muse Glimmer: An Open Agentic Model That Runs on Your Device | Meta AI Research<br>Skip to main contentTry Meta AI

Today, we're introducing Muse Glimmer, the next model from Meta Superintelligence Labs, and open sourcing the model weights under a permissive Apache 2.0 license.

Muse Glimmer is a 30-billion-parameter model optimized for always-on local agent workflows. It’s small enough to run on a Mac or PC with a single consumer GPU, enabling use cases that range from local agents and function calling, to local coding, and LLM-as-a-judge evaluation. Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category.

Foundation models have achieved remarkable capabilities across reasoning, code generation, and tool use — yet most deployments still depend on cloud infrastructure and network access. Running models locally enables you to use AI anywhere, anytime, with or without an internet connection. This is increasingly viable: the open source community has shown that smaller models, when trained effectively, can approach frontier-level performance on targeted tasks. Muse Glimmer is optimized for these local use cases.

Keeping with our long tradition of sharing fundamental AI research, we're releasing Muse Glimmer open weights today on Hugging Face, along with developer documentation to help you start building and running your own agents. Muse Glimmer is built to work with the tools developers already use. Optimized integrations on llama.cpp, MLX, and ExecuTorch will land in the coming days, so you can go from download to working agent in minutes.

How We Trained Muse Glimmer

An agent that manages your schedule, drafts your messages, organizes your files, and learns how you work needs deep access to personal context. It also needs several capabilities working in concert: long-horizon execution, precise tool calling, multimodal understanding, long-context memory, and instruction following.

We designed Muse Glimmer to balance capability against the memory and compute constraints of local hardware. This required a compact architecture, a novel distillation recipe that transfers agentic reasoning from a much larger teacher model, and inference optimizations — including quantization — to meet latency expectations. We achieved this in the following phases:

Pre-Training. We trained Muse Glimmer on Muse Spark's outputs using logit distillation, leveraging a similar data mix as the teacher.

Mid-Training. We trained the model on longer-context, more agent-heavy data with richer reasoning traces, alongside organic data.

Post-Training. We combined supervised fine-tuning with a mix of on-policy distillation and reinforcement learning across general, reasoning, coding, and agentic domains.

Muse Glimmer was evaluated under the standards set out in Meta's Advanced AI Scaling Framework and assessed for open-weight release across all relevant categories.

Built for Agents: What Muse Glimmer Can Do

Building effective agents requires key capabilities working together to achieve the user’s goals. Muse Glimmer is trained and evaluated across each of the following:

End-to-end Agentic Task Completion. Muse Glimmer achieves strong success rates on full-task benchmarks including DeepSearch QA, MCP-Atlas, 𝛕-Bench and SWE-Bench, which measure its ability to work within scaffolds, write and debug code, and resolve multi-turn requests from start to finish.

Reliable Tool Use. The model handles a wide range of function calls, invoking tools with precise schemas throughout extended workflows.

Multi-Step Reasoning. Muse Glimmer chains reasoning over long horizons, sustaining coherent plans across complex, extended workflows.

Failure Recovery. When a tool call fails or returns an unexpected result, the model is trained to diagnose the error and retry rather than halt.

Multimodal Input and Reasoning. Through a dedicated perception encoder, the model accepts interleaved text and images. This enables agents to interpret screenshots, charts, and documents alongside conversation.

Scaffold Compatibility. Muse Glimmer works across OpenClaw and other agentic orchestration patterns.

Controllable Effort. Muse Glimmer supports different reasoning strengths to select the right balance between quality and speed.

Multilingual. Muse Glimmer is trained on data from more than 100 languages.

Performance

We evaluated Muse Glimmer across a broad range of benchmarks to assess the diverse capabilities required for effective autonomous agent behavior. Compared with Gemma4-31B and Qwen3.6-27B, Muse Glimmer performs strongly for its size class on several widely used LLM benchmarks.

For more detail about our evaluations, see our report.

Optimized for Local Deployments

A local agent is truly useful if it's fast enough to feel responsive. An agent that takes minutes to reply or plan its next step breaks the flow of real work. We applied two optimizations to make...