Skip to main content
y.computer
Get a U.S. quote

Y Computer · U.S. founding line

Your private AI. Ready on day one.

Y Computer is a tested AI workstation plus Y OS: selected models, a private workspace, local APIs, agent controls and a benchmark report from your exact machine.

Join the U.S. founding batchExplore Y OS
Representative compact Y Computer Mini chassis
Personal

Y Computer Mini 128

Mini 128

One primary user who wants serious local models in a quiet desk box.

The most model capacity per dollar and watt in the line.

Processor
AMD Ryzen AI Max+ 395
AI memory
128GB unified memory
Accelerator
Radeon 8060S integrated GPU
Storage
2TB NVMe
Format
Compact, single-box desktop

A good fit for

  • 35B-class coding and multimodal models
  • 120B sparse reasoning models
  • Private chat, documents, voice and one agent loop

Optimized for one primary user; long context and concurrent jobs share the same memory pool.

$5,999

target starting price · before tax and shipping

Request this configuration
Representative dual-accelerator Y Computer Pro tower
Team

Y Computer Pro 64

Pro 64

Studios and small teams serving several local assistants at once.

Two high-memory accelerators tuned for throughput and value.

Processor
AMD Ryzen Threadripper 9960X
AI memory
256GB ECC system memory
Accelerator
2× Radeon AI PRO R9700 · 64GB aggregate VRAM
Storage
4TB NVMe
Format
Tower workstation · dedicated circuit recommended

A good fit for

  • Several simultaneous local assistants
  • 70B-class quantized models across both GPUs
  • Parallel chat, code, transcription and image services

The 64GB figure is aggregate capacity. Models must be explicitly sharded; two GPUs do not automatically mean twice the speed.

$11,999

target starting price · before tax and shipping

Request this configuration
Representative Y Computer Max 96 workstation tower
Maximum compatibility

Y Computer Max 96

Max 96

AI teams that need 96GB on one CUDA GPU and broad application support.

The cleanest single-GPU path to high-quality local inference.

Processor
AMD Ryzen Threadripper 9960X
AI memory
256GB ECC system memory
Accelerator
NVIDIA RTX PRO 6000 Blackwell Max-Q · 96GB ECC
Storage
4TB NVMe
Format
Tower workstation · dedicated 120V/20A circuit recommended

A good fit for

  • 120B sparse models on one GPU
  • High-fidelity 70B-class models
  • CUDA-first agents, serving and creative applications

For models larger than 96GB or heavier concurrency, a dual-GPU Max 192 is quoted after workload validation.

$24,999

target starting price · before tax and shipping

Request this configuration

Included with every system

The box is only half the product.

Anyone can order components. We turn them into an appliance your team can use without learning a new infrastructure hobby.

See everything in Y OS
  1. 01

    Y OS, installed

    Managed runtimes, private chat, local knowledge, voice, agent controls and one authenticated local API.

  2. 02

    Models for your work

    We choose formats that fit the memory and duty cycle, then pin the exact model and runtime versions.

  3. 03

    Measured before handover

    Your report records model hash, quantization, context, runtime, power profile and single- and multi-request results.

  4. 04

    A system you can recover

    Encrypted storage, signed pinned releases, pre-update snapshots and a documented rollback path.

U.S. launch path

Quote first. Payment after the facts.

Before we take payment, your written quote states the exact components, lead time, warranty owner, return terms, shipping and estimated sales tax. That is slower than a blind checkout button and much faster than fixing a bad $25,000 order.

  1. 1

    Fit call

    Workload, users, data boundary and the models you actually need.

  2. 2

    Written build

    Final BOM, price, lead time, warranty and benchmark profile.

  3. 3

    Build and handover

    Burn-in, Y OS onboarding and your machine-specific report.

Questions before the quote

Are these final retail prices?
They are founding-batch target starting prices for the stated configurations. Component supply—especially high-memory GPUs—moves quickly. We confirm the exact bill of materials, shipping, state sales tax and final price in writing before asking for payment.
Does all data stay local?
Local models, document search, transcription and the local API do not require an external AI provider. Optional web search, cloud models, email and other connectors can send data outside your network; Y OS labels those surfaces as External before they are enabled.
Can I install my own models?
Yes, through a reviewed model profile. Y OS keeps the privileged production runtime on pinned, hashed builds so an arbitrary uploaded model cannot silently execute unreviewed code as an administrator.
Which one should I buy?
Mini 128 is the best first system for one power user. Pro 64 is for parallel services and small teams willing to use a qualified AMD software image. Max 96 is for maximum CUDA compatibility and models that need up to 96GB on one GPU.

U.S. founding batch

Tell us what you want running locally.

Talk to an engineer