Resources

Practical guides on private AI, on-premise LLM deployment, and self-hosted AI for Australian businesses. Written by people who actually run this stuff.

Coming soon

We're writing up our experience deploying private AI systems for Australian businesses. Expect articles on choosing the right GPU, setting up Ollama and vLLM, securing on-premise AI, and what it actually costs to run your own AI instead of paying per-seat cloud subscriptions.

Why your law firm shouldn't use ChatGPT

Client privilege, data sovereignty, and why on-premise AI is the safe choice for legal practices.

In progress

How to choose a GPU for AI inference

VRAM vs bandwidth, 3090 vs 4090 vs 5090 vs workstation cards, and what actually matters for LLM workloads.

Planned

Ollama vs vLLM: which one should you use?

Two great inference engines with different strengths. Here's how we pick for each client.

Planned

What does private AI actually cost?

Hardware, software, power, and support. A transparent breakdown of what on-premise AI really costs vs cloud subscriptions.

Planned

Securing on-premise AI: a practical guide

Encryption, network segmentation, access controls, and backup strategies for private AI deployments.

Planned

RAG explained without the hype

Retrieval-augmented generation in plain English. How it works, what it's good for, and where it falls short.

Planned

Want to know when we publish?

We'll send new articles straight to your inbox. No spam, no marketing fluff, just practical guides.

Get in Touch