Meta and Apple Collaborate: Muse Spark Open 816B MoE Model Runs Locally on Dual Mac Studios via MLX
Meta released the open weights for Muse Spark Open, an 816B-parameter model optimized by Apple for its MLX framework. By leveraging sparse expert routing (activating only 42B parameters per token), the model can run locally on two linked M5 Ultra Mac Studios with 512GB unified memory each. This collaboration marks a significant breakthrough in deploying massive MoE models on Apple hardware, particularly benefiting coding agent applications.
Full Report
Rohan Paul (@rohanpaul_ai) · 2026-10-15 21
After years of rivalry, Meta and Apple join hands to deliver open-weight AI to the Mac.
Meta released the weights for Muse Spark Open, an 816B-parameter model that runs on 2 linked Mac Studios.
Apple tuned the release for its MLX framework. Only 42B parameters fire per token because the model routes each token to 8 of 256 experts, so every step reads a small slice of memory.
Holding the whole model is the hard part, since the 4-bit NVFP4 version needs at least 700GB of GPU memory.
Each M5 Ultra Mac Studio gives its GPU up to 512GB of unified memory, so 2 machines hold the model while 1.2TB/s of bandwidth feeds each token.
On the benchmarks, Muse Spark Open does top the MCP-Atlas tool-use test at 89.2, which suits the coding agents Meta built it for.
The license allows free commercial use but requires a “Built with Muse Spark Open” label, plus a separate Meta deal for API model sellers with over $20M in 12-month revenue.
Apple hasn’t priced the 512GB Mac Studio, and a cluster of 4 machines with 256GB each costs roughly $38,000.
↳ 引用 @rohanpaul_ai (Rohan Paul): Meta released the weights of Muse Spark Open, on Huggingface, an 816B-parameter model built for coding and agentic work.
The open version shares the same base model as Muse Spark 1.3, with additional safety post-training to resist misuse as a standalone model without system guardrails, reversing Meta’s first proprietary, closed-weight frontier model strategy from April.
Each of its 62 layers holds 256 expert networks and routes every token through 8, so deployment needs the memory of an 816B-parameter model but runs at the speed of a 42B model.
That storage bill explains the Apple tie-up, because the M5 Ultra pushes 1.2 TB/s of unified memory and a Mac Studio can carry up to 512GB.
A 3-bit quant tested on a 512GB M3 Ultra took about 344 GB and ran at about 21 tok/s generation on a short prompt.
