---
格式版本: 2
标题: "Run Local Agentic AI Workflows with Meta’s Muse Glimmer on NVIDIA"
原文链接: "https://developer.nvidia.com/blog/run-local-agentic-ai-workflows-with-metas-muse-glimmer-on-nvidia/"
发布日期: "2026-08-10"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "rule:scrape:strict_html_metadata"
发布时间证据: "article:published_time: 2026-08-10T13:27:19+00:00"
发布时间校准原因: "规则确认唯一严格发布时间，来源 scrape:strict_html_metadata"
发布时间校准置信度: "high"
发布时间候选数量: 14
发布时间严格候选数量: 2
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-11T21:10:37+08:00"
发布时间仲裁状态: "skipped"
发布时间仲裁尝试次数: 0
发布时间仲裁耗时毫秒: 0
发现时间: "2026-08-11T21:09:57+08:00"
入库时间: "2026-08-11T13:10:37.349Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://developer.nvidia.com/blog/"
匹配关键词:
  - "AI"
  - "GPU"
  - "NVLink"
  - "deployment"
  - "performance"
  - "latency"
  - "throughput"
相关厂家:
  - "NVIDIA"
  - "Meta"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 25
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文为NVIDIA上运行Meta的30B模型，仅讨论本地推理和工作流，未涉及超节点/AI Rack/机柜级系统、供电、散热、互连等核心主题，与项目范围无关。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-11T21:10:51+08:00"
AI主题相关性: 0
AI来源权威性: 15
AI新颖性: 0
AI技术细节: 0
AI商业部署信号: 0
AI完整性: 10
采集批次: "2026年8月11日21点09分57秒"
采集批次ID: "20260811-210957-092"
去重键: "https://developer.nvidia.com/blog/run-local-agentic-ai-workflows-with-metas-muse-glimmer-on-nvidia"
---

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](https://developer.nvidia.com/blog/building-for-the-rising-complexity-of-agentic-systems-with-extreme-co-design/), 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.

Muse Glimmer uses a dense architecture that activates every parameter for each token it processes, with no routing, expert selection, or variance across token pathways. As a result, it excels at agentic workloads that demand reliable instruction following, long-context coherence, predictable latency, and fewer failure modes.

![Side-by-side diagram, showing a dense model activating all 30B parameters per token versus an example of an MoE model routing to 2 of 7 experts ](https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/Dense-Vs-MoE.webp)

Figure 1. Overview of the Muse Glimmer dense model architecture compared to MoE architecture

## Privacy by design across local hardware

Agentic workflows involving personal files, communications, credentials, and proprietary documents require inference that never leaves the machine. Muse Glimmer hits an optimal balance. It’s large enough for complex multi-step reasoning, but small enough to fit within the VRAM of a single NVIDIA GPU, with no need for model sharding, CPU offloading, or using external endpoints.

NVIDIA Tensor Core architecture accelerates exactly this compute pattern, enabling real-time agentic inference fully on device at full context length.

- NVIDIA [GeForce RTX 5090](https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5090/) pairs 32 GB of VRAM with fifth-generation Tensor Cores, bringing Muse Glimmer to local developer devices, keeping proprietary code on device, and eliminating per-token inference cost.
- NVIDIA [DGX Spark](https://www.nvidia.com/en-us/products/workstations/dgx-spark/) brings workstation-class performance and enterprise agentic pipelines into a compact system. NVIDIA NVLink provides high-speed access to memory, and NVIDIA NIM containers make local Muse Glimmer deployment a one-command operation.
- NVIDIA [DGX Station](https://www.nvidia.com/en-us/products/workstations/dgx-station/) brings rack-scale Blackwell Ultra compute to on-prem enterprise environments for teams operating under air-gap mandates or compliance frameworks where cloud inference isn’t an option.
- NVIDIA [Jetson](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/) extends local Muse Glimmer inference to the edge, enabling robotics, industrial automation, and embedded systems, where network isolation is a hard requirement, and every inference decision must happen at the point of action.

## Optimized Muse Glimmer Performance on NVIDIA Blackwell Ultra

On NVIDIA Blackwell Ultra, Muse Glimmer delivers over *20K tokens/sec/GPU* at BF16/NVF4 precision, with the throughput-interactivity curve showing the 30B dense architecture sustaining high concurrency without the routing overhead of MoE models.

A single Blackwell Ultra handles the full model in VRAM with headroom for large KV cache buffers, making it well-suited for high throughput and low latency that developers need to run always-on agents entirely on local infrastructure.

![Muse Glimmer on NVIDIA Blackwell Ultra via vLLM, delivering over 20K tokens/gpu. ](https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/20K-Throughput.webp)

Figure 2. Muse Glimmer performance on NVIDIA Blackwell Ultra throughput at BF16 precision

## Building and fine-tuning agentic use cases

Run [NVIDIA NemoClaw](https://www.nvidia.com/en-us/ai/nemoclaw/) in a secure OpenShell environment to create long-running personal assistants powered for tasks like code generation, personal assistant, autonomous support, and more.

![Architecture diagram showing the NemoClaw OpenClaw agent harness connected to Muse Glimmer via vLLM on DGX Spark. ](https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/NemoClaw-vLLM-DGX-Spark.webp)

Figure 3. Muse Glimmer running locally with the NemoClaw agent harness in a governed sandbox, served by vLLM on DGX Spark

Developers can further post-train the model using the NVIDIA [NeMo AutoModel](https://github.com/NVIDIA-NeMo/Automodel/blob/main/docs/model-coverage/vlm/muse/muse_glimmer.mdx) with high-throughput efficiency, which is a fine-tuning library for native Hugging Face checkpoint support with no model conversion requirements.

It enables full SFT and LoRA fine-tuning out of the box, optimized for rapid experimentation on NVIDIA GPUs, including DGX Spark. Developers can also perform reinforcement learning with NeMo RL, with [sample recipes](https://github.com/NVIDIA-NeMo/RL/tree/muse-glimmer-support) and reference accuracy [validation curves](https://github.com/NVIDIA-NeMo/RL/blob/muse-glimmer-support/docs/guides/models/muse-glimmer.md).

![](https://www.youtube.com/watch?v=ayeHlacQNNA)

*Video 1. Run NeMoClaw and vLLM on DGX Spark*

## Flexible deployment paths for Muse Glimmer

NVIDIA supports multiple inference stacks to meet a variety of developer needs.

[SGLang](https://docs.sglang.io/cookbook/autoregressive/Meta/MuseGlimmer) and [vLLM](https://recipes.vllm.ai/meta-models/Muse-Glimmer-30B) provide open-source inference recipes for developers who require deeper control over performance on the NVIDIA accelerated platform.

It’s also available as a downloadable [NVIDIA NIM](https://catalog.ngc.nvidia.com/orgs/nim/meta/containers/muse-glimmer/-), a prebuilt, optimized inference container that auto-selects runtime configuration and serving setup, so teams can focus on building and scaling agents.

## Get started with Muse Glimmer and local AI agents

To get started, download Muse Glimmer weights from [HuggingFace](https://huggingface.co/meta-models/Muse-Glimmer-30B) and deploy using the inference recipes above, or pull the [downloadable NIM](https://catalog.ngc.nvidia.com/orgs/nim/meta/containers/muse-glimmer/) for a production-ready container on any NVIDIA GPU-accelerated platform. To call a hosted endpoint instantly, try it on [build.nvidia.com.](https://build.nvidia.com/meta/muse-glimmer-30b) For edge deployments on Jetson, explore the [Jetson AI Lab.](https://www.jetson-ai-lab.com/models/muse-glimmer-30b/?ncid=so-link-308924-vt48)