8/10/2026, 1:01:43 PM · enterprise-agents

Meta Launches Muse Glimmer: Open-Weight 30B Agentic Model Targets Consumer Hardware

Meta Superintelligence Labs releases Muse Glimmer, a 30-billion-parameter open-weight model designed to run fully local, always-on AI agents on a single consumer Graphics Processing Unit.

Overview

Meta Superintelligence Labs on August 10, 2026 released Muse Glimmer, <cite index="5-1,5-2">a 30-billion-parameter open agentic model whose weights are published under a permissive Apache 2.0 license.</cite> <cite index="5-3,5-4">The model is optimized for always-on local agent workflows and is small enough to run on a Mac or PC with a single consumer Graphics Processing Unit (GPU), enabling use cases that range from local agents and function calling to local coding and Large Language Model (LLM)-as-a-judge evaluation.</cite>

Architecture and Quantization

<cite index="15-10,15-11">At full precision, a 30-billion-parameter model would require over 55 GB of memory — far more than any consumer GPU offers. Meta uses quantization techniques to compress the model's weights to approximately 4-bit precision, shrinking the language model to under 20 GB.</cite> <cite index="15-12,15-13">This leaves enough headroom for the model's working memory (its KV cache), the perception encoder for image understanding, and the speculative-decoding drafter to run simultaneously within a 24 GB or 32 GB envelope, with Meta validating that this compression introduces minimal to no degradation on agentic tasks.</cite>

<cite index="6-12">A lightweight DFlash-based companion model proposes blocks of tokens that the main model then verifies in parallel</cite>, enabling practical inference speeds on local hardware. <cite index="1-10">Early performance testing shows Muse Glimmer 30B reaching up to 24 tokens per second on an AMD Ryzen AI Max+ 395 processor.</cite>

Training Pipeline

<cite index="9-8">Muse Glimmer is distilled from Muse Spark, the model that Meta Superintelligence Labs presented in April of this year.</cite> <cite index="9-9">Training took place in three phases: logit distillation on the output of the larger model, mid-training with longer context and agentic data, and finally, supervised fine-tuning combined with reinforcement learning.</cite> <cite index="16-4">Meta evaluated Muse Glimmer under the standards of its Advanced AI Scaling Framework and assessed it for open-weight release across the relevant categories.</cite>

Agentic Capabilities

<cite index="4-3">Meta's Chief AI Officer Alexandr Wang stated that the model supports agentic use through planning, tool calls, result checking, and failure recovery.</cite> <cite index="1-12,1-13">Muse Glimmer 30B is designed for longer-arc workflows, including complex workflows that span multiple steps and sessions; it can manage memory, recover from failures, and continue across restarts, helping developers move beyond one-shot interactions toward agents that can take ownership of meaningful work.</cite> <cite index="14-5">The model supports over 100 languages, positioning it for global deployment rather than the English-first approach that characterized earlier lightweight models.</cite>

Benchmarks and Comparisons

<cite index="16-13">The model was compared with Gemma4-31B and Qwen3.6-27B and, according to Meta, performs strongly for its size class on several widely used LLM benchmarks.</cite> <cite index="16-6,16-7">Evaluation benchmarks include DeepSearch QA, MCP-Atlas, τ-Bench, and SWE-Bench, which measure the model's ability to work within scaffolds, write and debug code, and resolve multi-turn requests from start to finish.</cite>

Availability and Ecosystem

<cite index="6-4">The model is available on Hugging Face under the Apache 2.0 license.</cite> <cite index="11-13">Optimized support for llama.cpp, MLX, and ExecuTorch is due in the coming days, alongside planned access through Ollama, LM Studio, Unsloth, vLLM, SGLang, Together AI, Fireworks AI, and OpenRouter.</cite> <cite index="11-14">Meta is also working with AMD, Arm, Dell, Intel, and NVIDIA on device-level optimization, extending its open AI research into local agent systems.</cite>

<cite index="4-4">Meta's Chief AI Officer also indicated that open weights for Muse Spark 1.2 will follow soon.</cite>

Cross-references

Sources

  1. [1]
    Run Meta Muse Glimmer 30B on AMD Ryzen™ AI Max Agentic PCs and Radeon ™ GPUs
  2. [2]
    Meta Publishes Muse Glimmer As 30B Open Agentic Model - Phoronix
  3. [3]
    AI at Meta (@AIatMeta) on X
  4. [4]
    Meta Releases Muse Glimmer 30B Open-Weight Model
  5. [5]
    Introducing Muse Glimmer: An Open Agentic Model That Runs on Your Device | Meta AI Research
  6. [6]
    Meta releases Muse Glimmer for local AI agents
  7. [7]
    Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows. Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on consumer hardware like a Mac or PCs with performant GPUs. In keeping with our long tradition of sharing fundamental AI research, we’re releasing model weights under a permissive Apache 2.0 license. 🧵👇
  8. [8]
    Meta Muse Glimmer – open weights 30B local coding model | Hacker News
  9. [9]
    Meta releases Muse Glimmer as an open local agent model - Techzine Global
  10. [10]
    Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
  11. [11]
    Best Open-Source LLM Models in 2026: Coding, Local, Agentic AI, Benchmarks, and License
  12. [12]
    Meta introduces lightweight AI model for single computer use
  13. [13]
    Meta introduces Muse Glimmer 30B open-weight model for local agent workflows
  14. [14]
    Meta launches Muse Glimmer open-weight AI model
  15. [15]
    tokenring 2026 2 5 the open source revolution how metas llama series erased the proprietary ai advantage
  16. [16]
    ETFOptimize | High-performance ETF-based Investment Strategies