Question 1

Why on-premise instead of a private cloud LLM tenancy?

Accepted Answer

Privilege, sovereignty, and predictability. With on-premise, no prompt or completion ever leaves your network; you control every change window and every model upgrade. You also stop paying the silent cost of vendor changes — for example, Anthropic’s Opus 4.7 tokenizer change in April 2026 produces up to ~35% more tokens for the same input, an effective price increase the customer didn’t agree to. None of that happens on a unit you own.

Question 2

What can a single DGX Spark realistically run for a small team?

Accepted Answer

A single Spark comfortably runs Qwen3.6-32B or Gemma 4 31B at FP8 for interactive use by a small team, plus 70B-class models in batch / RAG mode. Honest caveat: decode speed on the largest open models is bandwidth-bound (~273 GB/s LPDDR5x), so single-user 70B chat is in the low single-digit tokens/sec range. The sweet spot for an AU SME is 7B–35B class for chat, with larger models reserved for overnight batch.

Question 3

Is one Spark enough for the whole firm?

Accepted Answer

It depends on concurrent users and workload. We size on assessment. For HA we recommend two Sparks linked over 200 GbE — combined 256 GB unified memory unlocks ~405B-class models at FP4 and gives you live failover. Beyond two units, we usually point clients at a DGX Station / H200 server instead.

Question 4

Which model should we run?

Accepted Answer

We are deliberately model-agnostic. The Model Lab on this page lets you filter by industry, licence and Spark size. For regulated SMEs we typically recommend Qwen3.6, Gemma 4 or Phi-4 Reasoning (all Apache 2.0 / MIT). We flag Llama 4 (Llama Community Licence — has EU geofencing and use-case restrictions) and DeepSeek (foundation lab geopolitics) explicitly so the buyer can self-select.

Question 5

How does this satisfy the Privacy Act, APRA CPS 230, AHPRA and Law Council guidance?

Accepted Answer

On-premise inference keeps you on the right side of every one of those frameworks because the regulated data never traverses a third-party service. We document the controls (encryption at rest with LUKS, network egress filtering, Open WebUI RBAC + audit log to your SIEM, OEM-supported hardware) and provide an APP 1.7-1.9 transparency artefact for the 10 Dec 2026 deadline. See our /solutions/healthcare and /solutions/professional-services pages for the industry-specific framing.

Question 6

How are updates and patching handled?

Accepted Answer

We run a quarterly health review, manage a controlled model-update mirror, and coordinate OEM ProSupport tickets for hardware. Crucially, the box does not push outbound to the internet — we pull updates through a controlled mirror on your schedule, so you never face a surprise model deprecation or tokenizer change.

Question 7

Will it work with Microsoft 365, SharePoint and our existing tools?

Accepted Answer

Yes. Open WebUI speaks OIDC for SSO into Entra ID, Okta or Keycloak, and supports MCP (Model Context Protocol) tools out of the box. We commonly wire SharePoint, OneDrive, SQL, and ticketing systems via MCP servers so the model can read what your team already has access to — under the same RBAC.

Your AI.
On Your Premises.
Under Your Privilege.

Frequently Asked Questions

Why on-premise instead of a private cloud LLM tenancy?

What can a single DGX Spark realistically run for a small team?

Is one Spark enough for the whole firm?

Which model should we run?

How does this satisfy the Privacy Act, APRA CPS 230, AHPRA and Law Council guidance?

How are updates and patching handled?

Will it work with Microsoft 365, SharePoint and our existing tools?

Your AI.On Your Premises.Under Your Privilege.

Frequently Asked Questions

Why on-premise instead of a private cloud LLM tenancy?

What can a single DGX Spark realistically run for a small team?

Is one Spark enough for the whole firm?

Which model should we run?

How does this satisfy the Privacy Act, APRA CPS 230, AHPRA and Law Council guidance?

How are updates and patching handled?

Will it work with Microsoft 365, SharePoint and our existing tools?

Your AI.
On Your Premises.
Under Your Privilege.