Meta’s Muse Spark Open runs on Apple’s M5 Ultra Mac Studios
Meta has open‑sourced its 816‑billion‑parameter Muse Spark Open model and, together with Apple, made it run locally on two to four M5 Ultra‑equipped Mac Studios.

Meta releases Muse Spark Open for on‑device use
Meta announced on October 15 that its new Muse Spark Open model – 816 billion parameters in total, with about 42 billion active per token – is now available for download on Hugging Face. The company describes it as “the most capable U.S. open‑weight model to date.”
Apple’s hardware makes it possible
Apple’s latest Mac Studio, powered by the M5 Ultra chip, provides up to 512 GB of unified memory per machine. Meta says two such machines can share a full terabyte of memory, effectively acting as a single super‑computer. The MLX framework distributes the model across two to four Mac Studios, allowing the entire weight set to stay on‑device.
What the setup costs
A base‑configuration M5 Ultra Mac Studio with 256 GB of memory starts at US$10,799. Running the full model across two machines therefore costs a little over $20,000, while a four‑machine configuration can exceed $40,000. In Canada the same base unit is listed at CAD 7,799, putting a two‑machine rig at roughly CAD 15,600 before taxes.
Performance claims
Meta’s benchmarks claim Muse Spark Open outperforms leading Chinese models (GLM 5.3 and Kimi K3) on agentic tasks and visual reasoning. In a X post, Mark Zuckerberg wrote, “Muse Spark Open — weights releasing today — runs great on new Mac Studios thanks to work with @johnternus and Apple.” Apple’s chief John Ternus replied, “Congrats to the team! Amazing to run a model of Muse Spark Open’s caliber and scale this efficiently, right from your desk.”
Why the partnership matters
For Apple, the demo validates the M5 Ultra’s unified‑memory architecture and its MLX framework as a platform for frontier AI. For Meta, offering an open‑weight model that can run locally gives developers a cloud‑free alternative and puts the company’s work on hardware that many creators already own.
Open‑weight vs. closed models
Meta also unveiled Muse Wonder, a more capable but closed model available only through its API. Muse Spark Open is the version developers can freely download, modify and run, subject to Meta’s licensing terms.
Looking ahead
Both companies said the collaboration does not signal a broader partnership, but the move highlights a growing trend toward on‑device AI that sidesteps cloud‑centric compute. Analysts expect more developers to experiment with large models locally, especially where data privacy and latency are paramount.
Key numbers
| What | Figure | Source |
|---|---|---|
| Model size | 816 billion total parameters, ~42 billion active per token | Meta press release |
| Context window | 1 million tokens | Meta documentation |
| Base Mac Studio price (US) | $10,799 | Apple product listing |
| Minimum two‑machine cost (US) | just over $20,000 | Gadget Review analysis |
| Maximum four‑machine cost (US) | over $40,000 | The Tech Portal report |
| Unified memory per M5 Ultra Mac Studio | up to 512 GB (two machines give 1 TB) | Meta statement |
| Weight download location | Hugging Face repository | Meta announcement |
In this story
| Name | Role in the story |
|---|---|
| Hugging Face | Host for model weight download |
| Mac Studio | Apple desktop used for running the model |
| Apple Inc. | Provider of M5 Ultra Mac Studio hardware |
| Meta Platforms | Developer of Muse Spark Open |
| M5 Ultra | Apple silicon chip powering Mac Studio |



