Apple Announces Mac Studio Powered by M5 Max and M5 Ultra

LinkAppleAnnouncement

Apple has introduced the updated Mac Studio featuring M5 Max and M5 Ultra processors, focusing heavily on demanding creative, software engineering, and local AI workloads.

Key points

  1. M5 Max features up to an 18-core CPU, 40-core GPU, 128 GB unified memory, and 614 GB/s memory bandwidth.
  2. M5 Ultra joins two M5 Max chips, offering up to a 36-core CPU, 80-core GPU, 512 GB unified memory, and 1.2 TB/s memory bandwidth.
  3. Targeted at local AI inference and training, supporting models such as Gemma, Kimi, Mistral, and FLUX on-device.
  4. Equipped with Thunderbolt 5 (up to 120 Gb/s) supporting compute clustering, external PCIe chassis, Wi-Fi 7, and Bluetooth 6.
  5. Available from 22 September.

Why it matters

Running frontier-tier open models locally requires substantial memory capacity and memory bandwidth. With up to 512 GB of unified memory, the M5 Ultra desktop offers engineering teams an on-premise alternative to cloud API tokens for agentic and coding workflows.

Analysis

Apple is explicitly marketing the Mac Studio as a local AI powerhouse. The inclusion of Thunderbolt 5 enables low-latency workstation clustering (such as with exo) and high-speed PCIe expansion. The massive unified memory pool positions the device directly against enterprise compute rigs for engineers running local LLMs and automated agents.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:Apple

    Apple Introduces New Mac mini Powered by M6 and M5 Pro

    Apple has announced a new generation of the Mac mini featuring M6 and M5 Pro chips. The ultra-compact 5-by-5-inch desktop focuses heavily on local AI inference, development workflows, and small-scale clustering.

    AI & LLMs· Announcement

  • X post:Ash Hart

    MCDMA Enables Bonded Thunderbolt 5 Connections in TensorFold on Apple M5 Ultra

    Developer Ash Hart has announced bonded pair Thunderbolt 5 connectivity within the MCDMA RDMA framework. Paired with the TensorFold inference engine across two Apple Mac Studios running M5 Ultra chips, the dual-cable link delivers an 83 percent throughput uplift for tensor and pipeline parallelism.

    216bookmarks24.3kviews

    AI & LLMs· Announcement

  • Repository:ashhart/MCDMA

    MCDMA: RDMA Memory Access Linking Mac Studio, NVIDIA Spark, and AMD Strix Halo

    MCDMA enables Remote Direct Memory Access (RDMA) across heterogeneous workstations. Built in C under Apache-2.0, it bridges Apple Silicon Macs via Thunderbolt with Linux hosts like NVIDIA DGX Spark and AMD Strix Halo to accelerate distributed AI workloads.

    178starsC

    AI & LLMs· Tool

  • Video

    Video:Heavy Metal Cloud

    Nvidia DGX Spark Hands-On: Setup, vLLM Serving, and Mac Studio Comparison

    Heavy Metal Cloud reviews the Gigabyte and ASUS Nvidia DGX Spark desktop units powered by the Grace Blackwell architecture. The video provides a step-by-step guide for local LLM serving using Docker, vLLM, and SparkRun, as well as media generation in ComfyUI, comparing real-world performance against a Mac Studio.

    AI & LLMs· Tutorial

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.