# Apple releases MLX update to run 816-billion-parameter model across Macs

_Published Friday, October 16, 2026 at 1:28 PM EDT · AI · Latest · Tier 2 — Notable_

![Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio — Primary](https://mlr.cdn-apple.com/media/MLX_icon_F001_TC_2048_2600_6439f2ba0f.png)

Apple released an MLX update that it says runs the 816-billion-parameter Muse Spark Open model across four Mac Studios at over 36 tokens per second. The open-source framework distributes inference across Apple silicon computers, allowing developers to serve the model locally for tools such as coding agents.

The setup uses low-latency communication over Thunderbolt and splits each model layer across machines. Apple tested the model in NVFP4, a four-bit format that reduces its memory footprint to about 493GB. Intermediate computations still prevent it from fitting on one Mac Studio. At a 65,536-token context, communication overhead made two-machine tensor parallelization slower at processing input than splitting successive layers between machines.

## Sources

- [machinelearning.apple.com](https://machinelearning.apple.com/research/mlx-distributed-inference)

---
Canonical: https://techandbusiness.org/newswire/da1dRcDqSAzWUKDtXe98X4
Published: 2026-10-16T17:28:13.341Z
Story chronology: 2026-10-16T13:43:48.000Z
Retrieved: 2026-10-16T19:50:07.390Z
Publisher: Tech & Business (techandbusiness.org)