Sovereign AI · FlexPondi + VS Platform

Your AI.
Your infrastructure.
Your control.

Put AI to work where your data lives. FlexPondi brings two ASUS Ascent GX10 AI supercomputers into a compact mini rack. VS Platform helps you deploy, secure and manage the local solution from one portal.

Private Ollama deployment2 × 128 GB GX10 nodes12 months VS Platform
FLEXPONDI™ AI MINI RACKLocal compute
Three-quarter view of the Flexpondi™ AI Mini Rack with a display, network switch, patch panel and two ASUS GX10 computers
2GX10 supercomputers
256 GBaggregate unified memory
10-inchmini rack format

Product visualization based on supplied photography. Two 128 GB models; memory remains distributed across nodes.

PRIVATE AI INFRASTRUCTURE. Managed by VS Platform.Deploy. Secure. Manage. ↓

Why sovereign AI

Keep intelligence close.
Keep control closer.

Sovereign AI puts your organization in charge of where its AI runs, how data is used and who can access it. Local compute makes that control practical when paired with clear policies and managed operations.

01 / DATA

Keep sensitive work local

Run inference and retrieval against internal documents on your own network. Configure prompts, source files, embeddings and outputs to stay within your environment.

02 / CHOICE

Choose your models

Select models and tools that fit your workflows, licenses and capacity. A private Ollama deployment gives teams a local starting point for assistants and LLM applications.

03 / OPERATIONS

Own the operating model

Set access and deployment policies, control updates and monitor the infrastructure. Bring the same repeatable approach to the next department or location.

04 / ECONOMICS

Plan around local capacity

Use owned compute for recurring workloads and reduce reliance on metered inference APIs. Size the system for your models, concurrent users and response-time needs.

The complete local solution

Desk-side hardware.
Enterprise ambition.

FlexPondi™ AI combines compute, networking, rack infrastructure, software and deployment support in one bundle.

Two ASUS Ascent GX10 systems use the NVIDIA GB10 Grace Blackwell platform also found in DGX Spark. Each selected node has 128 GB of unified CPU/GPU memory. A dedicated high-speed interconnect supports compatible distributed workloads, while the 10G switch connects the solution to your local network.

Explore FlexPondi AI
Front view of the Flexpondi™ AI Mini Rack showing its network equipment and two ASUS GX10 systems
Flexpondi™ AI Mini Rack · Front view

Included in your mini rack

  • 2 × ASUS Ascent GX10128 GB unified memory per node
  • Cluster interconnect cableNode-to-node connectivity for supported runtimes
  • 8-port 10G Ubiquiti switchLocal network connectivity
  • 10-inch mini server rackPatch panel, thermostat and power management
  • Private Ollama local LLM deploymentWith deployment support
  • 12 months of VS PlatformSubscription begins at purchase

256 GB is the total across two 128 GB systems, not a single shared memory space. Larger-model inference requires a supported distributed runtime, suitable quantization and sufficient memory for context and runtime overhead. Validate the target model and user load before deployment.

One platform for every edge location

Local AI.
Centrally operated.

VS Platform connects the hardware to an operating workflow: deploy approved services, enforce security policy and keep the solution supported throughout its life.

DEPLOY

From hardware to useful AI

Onboard supported nodes and roll out applications and AI services through a solution catalog. Establish a consistent configuration for each location.

Solution catalog
SECURE

Trust the node. Control access.

Use VS Platform’s hardware-backed identity and attestation on supported hardware, encrypted connectivity, role-based access and central policies.

Platform security
MANAGE

See and support every location

Monitor health and security posture, coordinate updates and manage the application lifecycle through one portal as your footprint grows.

Meet VS Platform

Define your data boundary

Local processing.
Deliberate connections.

A private deployment starts with a clear map of what stays on-site and what is allowed to connect.

Configure applications to keep inference and retrieval local. Review outbound APIs, telemetry, backups, remote access and agent tools against your data policy. Central management and local inference serve different purposes.

Local hardware alone does not establish regulatory compliance or an air-gapped environment. VS Platform’s remote operations require connectivity; verify supported hardware and the management data flow during solution design.

YOUR ORGANIZATION’S NETWORK
Your users & applications
↓
Private Ollama · Local models & retrieval
↓
FlexPondi · 2 × ASUS GX10
Local inference data path
VS Platform control planeDeployment · policy · health · updatesApproved encrypted management connection

Put it to work

Start with a workload.
Build a repeatable solution.

Internal knowledge assistants

Search and summarize approved internal material through local retrieval and inference, with access aligned to the underlying information.

Enterprise teams · Private AI labs

Operational copilots

Help teams query manuals, maintenance procedures and site knowledge close to the systems and people doing the work.

Manufacturing · Warehousing · Retail

Local AI development

Prototype agents and AI applications on a Linux and NVIDIA CUDA foundation, then validate the workload before broader rollout.

Robotics · Security operations · Edge computing

Questions, answered.

Does sovereign AI mean that nothing leaves the rack?

It means designing for organizational control. Inference can run locally, but configured applications, external tools, monitoring, backups and remote management may move data. Define and validate those flows as part of deployment.

Are the ASUS GX10 systems NVIDIA DGX Sparks?

The ASUS Ascent GX10 is ASUS’s own system based on the NVIDIA GB10 Grace Blackwell platform used in NVIDIA DGX Spark. This bundle specifies two ASUS Ascent GX10 systems with 128 GB of unified memory each.

Can two nodes run any 400B-parameter model?

No. A parameter count alone does not determine fit or speed. Precision, quantization, context length, runtime support and concurrency all affect capacity. Validate the exact model and distributed runtime on the two-node configuration.

Does a second node automatically provide failover?

No. Nodes can serve separate workloads or participate in supported distributed inference. Resilience and failover require an application architecture and configuration designed for that purpose.

What is included beyond the hardware?

The bundle includes a private Ollama local LLM deployment, deployment support and 12 months of VS Platform subscription service from the time of purchase. Confirm ongoing subscription and support options with Portal Robotics.

Enterprise AI. Anywhere.

Bring AI to your data.
Keep control of the outcome.

Walk through your workload, data boundary and two-node deployment with Portal Robotics.

Product details: FlexPondi AI · VS Platform · ASUS Ascent GX10 specifications

Watch a new site come online in minutes, not months.

A 30-minute walkthrough of VS Platform on your use case: onboarding a node, standing up a secure network, deploying from the catalog, and seeing it all in one portal.