◆ AI AGENT BOX

The cloud isn't where
AI has to live.

A production-grade appliance running local LLMs at 300+ tokens per second. No cloud tokens. No per-seat bills. No data leaving your walls. Deploy in 3 to 10 days. Operate on fixed cost. Own your AI stack.

300+tokens / sec
128GBunified memory
70Bparams local
3–10days to deploy
yGen AI AGENT BOX PWR
PROCESSOR
AMD AI MAX+ 395
RUNTIME
Ollama · Local
FORM FACTOR
19.3 × 18.6 × 7.7 cm
CONNECTIVITY
Tailscale-secured
◆ THE CIO PROBLEM

Cloud AI is an
OPEX time bomb.

Per-seat pricing. Per-GB ingestion. Per-token inference. Variable bills that scale with usage — usually in the wrong direction.

Meanwhile: your data leaves your perimeter. Your compliance team writes memos. Your CFO writes checks.

AI Box is the counter-narrative.

— FIXED COST · ON-PREM · YOURS
◆ SPECIFICATIONS

Built for production.
Priced to own.

Every spec is chosen to run real workloads — not a chat demo. Local inference at production scale.

ComputeAMD AI MAX+ 395 · Radeon 8060 Graphics
Memory128GB LPDDR5X 8000 · on-board unified
Storage2TB NVMe PCIe 4.0 · expandable to 16TB
Throughput300+ tokens / sec · local inference
Model supportUp to 70B parameter models · 8K+ context
Runtime stackOllama · LLaMA · Qwen · Mistral · GPT-OSS
RAG infrastructureMongoDB + Qdrant · vector DB per tenant
Connectivity2.5 Gigabit · WiFi 7 · BT 5.4 · Tailscale VPN
Form factor19.3 × 18.6 × 7.7 cm · VESA-mountable
PowerDC 19V / 11.8A / 230W
Deployment time3 to 10 days · plug-and-play
Warranty2 years · with optional yForce support retainer
◆ THREE DEPLOYMENT MODES

Three ways to run it.

From single-site pilots to multi-tenant production clusters — pick the architecture that matches your scale.

DEPLOYMENT 01

Home Edge

PROOF-OF-CONCEPT · SINGLE-SITE

Single-site deployment for pilots, small clinics, field offices. Encrypted tunnel back to HQ data center. Full tenant isolation, no inbound ports exposed.

  • WireGuard / Tailscale VPN
  • RAG-only API access mode
  • Multi-tenant isolation built-in
  • Sandbox / non-production safe
DEPLOYMENT 02

Colocation

PRODUCTION · MULTI-TENANT

Rack-mount at VITRO, STT Manila, or your preferred PH data center. Multi-tenant VLAN segmentation. Site-to-site VPN to client data centers.

  • ~2kW scalable rack deployment
  • VLAN-segmented multi-tenant
  • Azure hybrid optional
  • Site-to-site IPsec VPN
DEPLOYMENT 03

Hybrid

ENTERPRISE · MULTI-LOCATION

Edge boxes for latency-sensitive inference. Colocated cluster for heavy workloads. Cloud burst only where it makes sense. You decide where each workload lives.

  • Edge + Colo + selective cloud
  • Per-workload placement
  • Centralized monitoring
  • Failover & staging built-in
NOTE · Colocation is delivered through Philippine-based facilities (VITRO, STT Manila). Contracting is available through yGen Innovations Inc. (Philippines) or Keystone Apex Holding LTD (Singapore) depending on your jurisdiction and procurement requirements.
◆ ON-PREM vs CLOUD-NATIVE

Why on-prem wins.

A 500-endpoint client. Two cost models. The math is not subtle.

Dimension ◆ AI Box Cloud-Native AI
Cost model Fixed CAPEX Variable OPEX
LLM costs Zero · local inference $30–50 per user / month
Ingestion / storage Unlimited · local NVMe $2.76–5.22 per GB / day
Data sovereignty 100% on-premise Vendor cloud regions
Latency Local · 300+ tok/sec Internet-dependent · variable
Customization Full control · open stack Vendor APIs & guardrails
Lock-in None High · proprietary
Time to deploy 3–10 days Weeks to months
REAL-WORLD EXAMPLE · 500-ENDPOINT CLIENT

Cloud SOC: ~$15K to $50K per month, ongoing. AI Box: one-time investment. Payback in 6 to 10 months. Every month after that is margin.

◆ THE COMPLETE STACK

AI Box is the body.
Phoenix is the mind.

Every Phoenix agent, every RAG pipeline, every sandboxed Docker container — runs locally on AI Box. Zero dependency on cloud inference. Zero tokens sent outside your network.

Learn about Phoenix →
◆ BOOK A DEMO

See it in your
environment.

A walkthrough of the architecture, the ROI model, and a live deployment scenario tailored to your infrastructure — with our solution architects, not a sales rep reading slides.