06On-device

One Laptop, Three Engines

The match data could not leave our hands, so the compute came to the data. One Snapdragon X Elite laptop: its CPU decodes a full match in under 10 seconds, and its GPU and NPU are the headroom for local models.

  1. 01This laptop
  2. 02Three engines
  3. 03Today: the CPU
  4. 04Next: local models
  5. 05Why hardware

01This laptop

Where every byte stayed

Our system on chip: twelve Oryon CPU cores, an Adreno X1-85 GPU and a Hexagon NPU sharing 32 GB of memory ORYON CPU · 12 CORES 01020304 05060708 09101112 ADRENO GPU · X1-85 HEXAGON NPU SHARED MEMORY · 32 GB
Spec sheetRead locally with Get-CimInstance
  • DeviceSnapdragon X Elite laptopthe only machine the match data ever touched
  • ProcessorSnapdragon X EliteX1E78100 · Qualcomm Oryon CPU
  • Cores12Oryon CPU cores
  • Memory32 GBsystem memory
  • GraphicsAdreno X1-85Qualcomm Adreno GPU
  • Storage1 TBinternal drive
  • SystemWindows 11 ProARM64 · 64-bit
How we read the specs
> 'Win32_ComputerSystem','Win32_Processor','Win32_PhysicalMemory',
  'Win32_OperatingSystem','Win32_VideoController','Win32_DiskDrive' |
  ForEach-Object { Get-CimInstance $_ } 

Published: device class, processor and core count, memory, graphics, storage, OS edition and architecture. Left out on purpose: serial numbers, user and host names, and anything else that identifies the device.

02Three engines

CPU, GPU and NPU on one chip

Snapdragon X Elite system on chip Abstract diagram of the Snapdragon X Elite. A Qualcomm AI stack layer (AI Engine, AI Hub, local LLMs and local models) feeds down into three engines on one chip: the Oryon CPU with twelve cores on our machine, the Adreno X1-85 GPU and the Hexagon NPU rated at up to 45 TOPS. Data pulses flow between all three over shared memory. Today our decoder runs on the CPU; vision models and local LLMs are next for the GPU and NPU. Everything stays on the device. ON-DEVICE · DATA STAYS HERE QUALCOMM AI STACK AI ENGINE CPU + GPU + NPU AI HUB DEVICE-READY MODELS LOCAL LLMS + LOCAL MODELS SNAPDRAGON X ELITE SYSTEM ON CHIP ORYON CPU · 12 CORES ADRENO GPU · X1-85 HEXAGON NPU 45 UP TO TOPS SHARED MEMORY TODAY: DECODER NEXT: VISION NEXT: LOCAL LLMS
  • Oryon CPU · 12 cores on our machine. Runs our decoder today.
  • Adreno GPU · X1-85 on our machine. Next: vision models.
  • Hexagon NPU · up to 45 TOPS. Next: local LLMs.
  • Shared memory · one pool for all three engines.

03Today

The CPU decodes a match

  • < 10 sfull-match decode, numpy only
  • 1 of 3engines used: the Oryon CPU
  • arm64native Linux container, offline
  • 0bytes sent off the machine

Our Initial Challenge solution ran on the Oryon CPU alone. The Adreno GPU and the Hexagon NPU sat idle.

04Next

Headroom for local models

  • Vision on device

    A light ball detector for the frames the tracker misses, running on the GPU or NPU, beside the data. It is the on-device vision engine on our roadmap.

  • Local LLMs

    Language models that turn possession numbers into tactical text, run locally with nothing sent anywhere.

45TOPS · HEXAGON NPU

The Hexagon NPU in our laptop is rated at up to 45 TOPS: trillions of operations every second, set aside for neural networks alone. It sat idle through the Initial Challenge. That idle silicon is our headroom.

Our measure

What we vouch for is what we ran ourselves: a full match decoded in under 10 seconds, on the CPU alone, with the network switched off.

Why hardware

Privacy is a place

The match data may not go to any cloud platform, external service or hosted model, so renting a GPU or calling a hosted API was never an option. A laptop strong enough to do the work means nothing has to leave it. Privacy and speed come from the same choice: computing locally.