Meta Muse Spark Open: An 816B AI Model That Runs on Two Mac Studios

On October 15, Meta released Muse Spark Open, an 816-billion-parameter open-weight model that it calls the most capable US open-weight model to date. The surprise is where it runs: Meta and Apple worked together so it fits on two M5 Ultra Mac Studios, on a desk, with no data center. Here is what Meta released, what it really takes to run it, what the license allows, and who should care.

For information only. This article is based on Meta's announcement and model card for Muse Spark Open, the Hugging Face launch post, and coverage by MacRumors, OfficeChai and Flavio Copes. TechVernia has no commercial relationship with Meta or Apple.

Frontier AI, Without the Data Center

For the past two years, using a top-tier AI model meant one thing: sending your prompts, your code and your documents to someone else's servers. The biggest open models existed, but running them yourself required racks of GPUs that only large companies could afford.

On October 15, 2026, Meta released Muse Spark Open, the open-weight sibling of Muse Spark, the closed model that powers Meta AI. Meta calls it "the most capable US open-weight model to date" and says it is the first model in its class that can run on a desktop: two Apple M5 Ultra Mac Studios, linked with Apple's MLX framework.

Apple was directly involved. CEO John Ternus congratulated the teams on X, calling it "amazing to run a model of Muse Spark Open's caliber and scale this efficiently, right from your desk." Two companies that rarely cooperate on AI chose to launch this together, and that alone says something about where the market is heading.

816B Total parameters (mixture-of-experts)
42B Active parameters per token
1M Token context window
2 Macs M5 Ultra Mac Studios, 512GB each

What Meta Released

Muse Spark Open is a mixture-of-experts (MoE) model. Instead of using all of its parameters for every word, it routes each token to a small group of specialists. According to the Hugging Face launch post, each layer has 256 experts and the router picks 8 per token. The result: 816 billion parameters of knowledge, but only about 42 billion doing the work at any moment, which keeps it much faster than its size suggests.

01
The Big Shift

From "AI as a Service" to "AI as Equipment"

The headline is not the parameter count. Larger open models have existed. The headline is the form factor. A model close to the frontier now runs on hardware a company can buy once, put in an office and own. No API bill per token, no prompt leaving the building, no dependence on a vendor's uptime or pricing changes. That is a different business model for AI, and Meta and Apple are betting on it together.

The Mac Studio Setup, Explained

Why Macs? Because of unified memory. On Apple Silicon, the CPU and GPU share one large pool of memory. An M5 Ultra Mac Studio can be configured with up to 512GB, and its memory bandwidth reaches about 1.2 TB/s, according to MacRumors. Link two of them with MLX, Apple's machine learning framework, and you get roughly 1TB of memory working as one machine: enough to hold the model.

Meta showed two demos on this setup:

The community is also already testing smaller quantized versions. The Hugging Face post reports that a 3-bit MLX version uses about 344GB on a single 512GB M3 Ultra and generates about 21 tokens per second, and a 2-bit llama.cpp version runs at about 18 tokens per second. Those versions trade some quality for size.

What It Really Takes to Run It

SetupWhat you need
Meta's desktop demoTwo M5 Ultra Mac Studios with 512GB each, linked with MLX
Full precision (BF16)About 1.5 TB of weights; around 2 TB of GPU memory per Meta's model card
Compressed (NVFP4)At least 700GB of GPU memory, NVIDIA Blackwell GPUs (for example a single B200 node)
Community quants on Mac3-bit MLX: about 344GB on one 512GB Mac. More than 256GB needed even at 3-bit
Hosted APIsGroq, Fireworks AI, Together AI, OpenRouter, Baseten, Modal, Nebius
Weight downloadsHugging Face, Amazon SageMaker AI, Google Cloud Model Garden, Microsoft Foundry
Inference enginesvLLM, SGLang, llama.cpp, MLX, Transformers, TensorRT-LLM, Unsloth

Be realistic: "local" here does not mean your laptop. The 512GB Mac Studio has not been released yet; MacRumors reports it is expected later this month, and the 256GB model already costs over $10,000. Two of the top configuration is a serious investment. For most individuals, the practical way to try Muse Spark Open today is through one of the hosted APIs.

The License: Open Weights, Not Open Source

Muse Spark Open ships under the Muse Model License, not under MIT or Apache. Meta says most developers can use it free of charge, and the license allows modification, fine-tuning and redistribution. But it comes with conditions, according to analyses of the license text:

If you plan to build a commercial product on it, read the license on the Hugging Face model page yourself, or ask your legal team, before you commit.

How It Compares

Meta says Muse Spark Open leads open rivals such as Nemotron 3 Ultra, Mistral Large 4, Qwen3.8, GLM 5.3 and Kimi K3 on tool-use and knowledge benchmarks like MCP-Atlas, JobBench, HLE-Diamond and AA-Omniscience. It also admits the model trails Kimi K3 and GLM 5.3 on Terminal-Bench 2.1, and reports indicate it trails them on the Artificial Analysis Intelligence Index and DeepSWE coding as well.

In other words: a top-tier open model, strong on agents and tools, but not the undisputed leader in pure coding. Note also the careful wording: "most capable US open-weight model", not most capable open model overall. Chinese labs still set the pace in several categories.

What to read with care. All benchmark results cited here come from Meta and were run at the highest reasoning effort (xhigh). Independent benchmarks are still pending. Real-world speed on the two Mac Studio setup has not been independently measured, and the 512GB Mac Studio is not yet on sale. Some outlets report that two to four Mac Studios can be paired; Meta's demo used two.

Who Should Care

02
Use Cases

Where Muse Spark Open Earns Its Place

  • Regulated companies: banks, hospitals, law firms and public bodies that cannot send code or client data to a cloud API.
  • Software teams: a strong coding agent running in-house, with a fixed hardware cost instead of a per-token bill.
  • Researchers: a frontier-scale model they can inspect, fine-tune and study in depth.
  • Startups: a way to reduce dependence on a single closed AI vendor and its pricing decisions.
  • Security teams: AI-assisted analysis of sensitive logs and code that should never leave the network.

How I Would Approach It

1. Start With a Hosted API

Before buying any hardware, run the model on OpenRouter, Groq or Together AI. A few dollars of tests will tell you whether its quality fits your work.

2. Test on Your Real Tasks

Take one real coding ticket, one long document and one multi-step workflow from your week. Compare the results with the model you use today, and note how many tries each one needs.

3. Do the Math

Compare a year of your current API spend with the price of the hardware plus electricity and maintenance. Local AI only wins when the volume is high or the data is too sensitive to leave.

4. Secure It Like a Server

Meta's model card recommends extra protections when the model uses tools. When you self-host, those guardrails become your job: restrict what the agent can access, log what it does and keep a human in the loop for anything critical.

Muse Spark Open proves that frontier-class AI can live on a desk. It is still expensive and the license has limits, but for teams with sensitive data or heavy usage, owning the model is now a real option, not a dream.

Frequently Asked Questions

What is Muse Spark Open?
It is an open-weight AI model released by Meta on October 15, 2026. It is a mixture-of-experts model with about 816 billion total parameters, 42 billion active per token, and a 1 million token context window, built for coding and agentic work.
How is it different from Muse Spark?
Muse Spark is Meta's closed model that powers Meta AI and is available through Meta's API. Muse Spark Open shares the name but publishes the full model weights, so anyone can download, run and fine-tune it under Meta's license.
Can I run it on my own computer?
Only on very high-end hardware. Meta's demo used two M5 Ultra Mac Studios with 512GB of memory each. Compressed community versions need more than 256GB of memory. Most laptops and desktop PCs cannot run it, so hosted APIs are the practical option for most people.
Is Muse Spark Open free for commercial use?
Meta says most developers can use it free of charge under the Muse Model License, which requires a "Built with Muse Spark Open" notice. Companies above $20 million in annual revenue need a separate agreement with Meta to offer it as a hosted service. Read the license before building a product on it.
Where can I download or try it?
Weights are on Hugging Face, Amazon SageMaker AI, Google Cloud Model Garden and Microsoft Foundry. Hosted APIs are available from Groq, Fireworks AI, Together AI, OpenRouter, Baseten, Modal and Nebius.
Is it better than Chinese open models like Kimi or GLM?
According to Meta's own benchmarks, it leads them on several tool-use and knowledge tests but trails Kimi K3 and GLM 5.3 on Terminal-Bench 2.1 and some coding measures. Independent benchmarks are not yet available.

My Take

As a network engineer, the part of this launch that excites me most is not the benchmark chart. It is the architecture diagram: a frontier-class model, two boxes on a desk, a cable between them, and no traffic leaving the building.

For years, the trade-off was simple: the best AI lived in the cloud, and if you wanted it, your data had to travel. Muse Spark Open does not erase that trade-off yet. The hardware is expensive, the 512GB Mac Studio is not even on sale, and the license is not truly open. But it shows the direction clearly. AI is starting to move from a service you rent to equipment you own.

My advice: do not buy two Mac Studios tomorrow. Try the model through an API, measure it on your real work, and do the math. If your data is sensitive or your volume is high, this may be the first time local AI really makes sense.

So, would you run a model this size locally, or does the cloud still win for you?

Sources:

This article is published for information purposes only, to help readers discover and evaluate new AI tools.

Related Articles:

Kodjo Apedoh

About the Author

Kodjo Apedoh

Network Engineer & AI Entrepreneur

Founder of TechVernia & SankaraShield. Certified Network Security Engineer with 4+ years of experience specializing in network automation (Python), AI tools research, and advanced security implementations. Also builds iOS and Android applications. Holds certifications from Palo Alto Networks, Fortinet, and Cisco. Based in Arlington, Virginia.

Connect on LinkedIn →