Published

Technology and Science15 October, 20263 min read

Meta Releases Muse Spark Open With 816B Parameters for Local Mac Studio Execution

This article is an automated aggregation of coverage from news outlets. Our editorials offer in-depth analysis curated by the NewsCord team.

Muse Spark Open has 816 billion total parameters, 42 billion active, and a 1,000,000-token context window. Runs locally on Mac Studio with M5 Ultra, optimized for Macs.

Read the story
Meta Releases Muse Spark Open With 816B Parameters for Local Mac Studio Execution
Image: Unite.AI

Shared framing

Three sampled publishers emphasise an unusual or repaired Apple-Meta relationship, a minority emphasis in a collection largely about the model and Mac compatibility. Separate headlines stress memory demands or licensing and competitive caveats.

3 of 27 outlets · 3 of 28 headlines analysed

Includes analysis, reporting.

  • Bolsamaniaput aside their differences and ally in AI
  • Axios"Mommy and daddy" play nice
  • TradingKeyin an unusual move
See the headlines

An unusual or repaired Apple-Meta relationship

Bolsamania says the companies put aside their differences, Axios uses a family metaphor, and TradingKey calls the move unusual. These phrases make the relationship itself an angle; headlines that merely say team up or join forces do not necessarily imply reconciliation. Axios’s metaphor is attributed to Meta AI chief Alexandr Wang.

Other angles in this collection

Heavy memory demands foregrounded

2 outlets · 2 headlines

El Ecosistema Startup and Startup Fortune foreground the memory requirement as a barrier to running the model. Both cite Engadget in their coverage, so their similar emphasis should not be taken as independent discovery. This is a hardware constraint, distinct from restrictions in the model licence.

Licensing and competitive caveats

1 outlets · 1 headlines

SQ Magazine’s headline foregrounds fine print and a gap against Chinese models. Its opening frames the release as a qualified achievement; it is the sole headline here with that combination, rather than part of a broader shared claim about memory requirements.

All 28 analysed headlines

Counts describe this collection. One headline may support more than one angle.

Analysed 16 Oct 2026.

Reviewed by Codex validator (AI) · 16 Oct 2026

Muse Spark Open Goes Local

Meta released the weights for Muse Spark Open, describing it as its most capable US open-weight model to date, and the model carries 816 billion total parameters with 42 billion active and a 1 million token context window. Meta said Muse Spark Open is natively multimodal with support across text, image, video and audio, and it is built specifically for coding and agentic work, including long-horizon tasks, multi-step reasoning, and complex software engineering. Meta also positioned the release around local execution, saying developers can run the model on a desktop setup built from Apple’s Mac Studio computers, pairing two to four Mac Studio computers with Apple’s M5 Ultra chip.

“Muse Spark Open is available today and brings leading agentic capabilities to your desktop for the first time on Apple M5 Ultra Mac Studios.”
Meta AI

Meta’s announcement tied the on-device pitch to Apple’s MLX framework, and Meta said “together they’re the best way to run a powerful model on your own desktop.” Meta and Apple framed the collaboration as a way to avoid cloud-only use, with Meta releasing the weights and Apple optimizing the Mac Studio path for running Muse Spark Open locally.

Image from 9to5Mac
Image: 9to5Mac
Reporting for this sectionMeta AI9to5Mac

Hardware, Benchmarks, and Scaling

Apple’s Apple Machine Learning Research post said MLX on Mac with Apple silicon lets AI researchers and developers experiment locally with the latest models and methods in a private environment. Apple said a cluster of four Mac Studios running Muse Spark Open generates over 36 tokens per second, and Apple described scaling from a single Mac Studio up to multiple Macs using RDMA over Thunderbolt driver. Apple compared Mac Studio generations by evaluating M5 Ultra and M3 Ultra, and Apple reported that TTFT speedups reached “up to 4.6× faster compared to an M3 Ultra.”

Apple also reported generation speed differences by tying them to memory bandwidth, and Apple said the Mac Studio with M5 Ultra reported “1.6× faster tokens/s.” Apple’s post also described memory constraints for Muse Spark Open, saying the model would require more than 1.6TB of RAM in native precision (BF16) for the model parameters alone, while a 4-bit quantized (NVFP4) format lowered the model memory footprint to about 493GB.

Image from Apple Machine Learning Research
Image: Apple Machine Learning Research
Reporting for this sectionApple Machine Learning Research

Partnership Stakes and Access

Mark Zuckerberg posted on X that “Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple,” and Apple CEO John Ternus replied publicly with a showcase for on-device AI performance. Meta AI chief Alexandr Wang said developers can run Muse Spark Open locally on Apple M5 Ultra Mac Studios, and Wang also described the practical reason that Mac Studios make enough memory available to run powerful open-weight models. Meta said Muse Spark Open is available today through API platforms at Baseten, Fireworks AI, Groq, Modal, Nebius, OpenRouter and Together AI, while Meta said the weights are available for download on Amazon SageMaker AI, Google Cloud Model Garden, Hugging Face, and Microsoft Foundry Models.

“Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.”
The Tech Portal

Meta said the model is released under the Muse Model License with limited commercial terms, and Meta said the open-weight version ships with custom, auto-tunable Helion GPU kernels in SGLang. Meta also said it evaluated Muse Spark Open in line with its Meta Superintelligence Scaling Framework, and Meta stated that the model met the thresholds the framework requires for release.

Reporting for this sectionThe Tech PortalMeta AI