Xiaomi AI Cube: Prototype Featuring Three XRING Chips and LPDDR6 Memory

LinkHilbert HagedoornNews

Xiaomi has unveiled the AI Cube, an engineering prototype compact PC powered by three proprietary XRING processors and LPDDR6 memory, designed to run local models with up to 120 billion parameters.

Key points

  1. Three-chip setup combining XRING O3, O100, and D100 silicon alongside a 16-core G2 Ultra NX GPU
  2. Employs LPDDR6 memory to provide higher bandwidth and efficiency across a unified memory pool
  3. Reportedly supports local models containing up to 120 billion parameters
  4. Operates at a sustained 150W power envelope within an aerospace-grade aluminium chassis
  5. Remains an engineering prototype with undisclosed memory sizes, storage, pricing, and release plans

Why it matters

The system underscores Xiaomi's push into proprietary silicon and reflects the broader shift towards vertically integrated compute platforms targeting local AI workloads.

Analysis

By uniting custom CPU, graphics, and AI acceleration around a unified memory pool, Xiaomi is directly following the architectural direction established by Apple and Qualcomm. While the 120-billion-parameter claim is ambitious for a 150W desktop form factor, key specifics regarding memory capacity and model quantization remain unannounced. Software compatibility will be the decisive factor, particularly if the custom silicon relies on a non-x86 instruction set.

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:Xiaomi MiMo Team

    Xiaomi Releases MiMo-V2.5-Pro as Open Source

    Xiaomi has unveiled MiMo-V2.5-Pro, an open-source Mixture-of-Experts model featuring 1.02 trillion total parameters with 42 billion active. The model supports a 1M-token context window and is specifically designed for complex agentic workflows and long-horizon software engineering.

    AI & LLMs· Announcement

  • 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

  • Link:inclusionAI

    Ling-3.0-tiny: Lightweight Hybrid Reasoning MoE Model by inclusionAI

    inclusionAI has introduced Ling-3.0-tiny, a compact MoE model with 7.9B total parameters activating only 1.3B parameters per token. Utilizing a hybrid architecture of linear and latent attention mechanisms, it aims to deliver efficient reasoning and agentic workloads on local hardware.

    AI & LLMs· Tool

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.