REX: Or How I Justified Buying a 7950X3D for 'the Lab'
There’s a specific moment every home lab builder knows well. You’re staring at a PC Part Picker list at 11pm, the cart has somehow grown to $8,000, and you’re drafting a mental justification document that rivals an enterprise budget proposal. The difference is, the approver is your future self, and your future self is easily bribed.
That was REX.
The Brief (That I Wrote for Myself)
The stated goal was simple: a machine capable of running local AI workloads, multiple Hyper-V VMs, and GPU inference — simultaneously — without thermal throttling into the shadow realm. The unstated goal was to have the most capable homelab on the street, which is a low bar when your neighbours are mostly retirees, but still counts.
The final spec:
- AMD Ryzen 9 7950X3D (16 cores, 3D V-Cache — because cache is king for VM density)
- 128GB DDR5 RAM (because “64GB should be enough” is something people say right before it isn’t)
- RTX 5090 (for local LLM inference — this is load-bearing hardware, not gaming, I promise)
- 4× NVMe drives in dedicated roles: OS, gaming, media, and a ReFS Dev Drive for the lab
- Windows 11 Pro as the host (controversial, I know — we’ll get to that)
Why Windows as the Host?
The choice to run Windows 11 Pro as the hypervisor host instead of Proxmox or ESXi is the thing that raises the most eyebrows in homelab circles. The answer is boring and practical: Hyper-V on Windows gives you a Type-1 hypervisor with a usable desktop environment, DirectX GPU passthrough that actually works, and WSL2 for Linux workloads without spinning up another VM just to run bash.
WSL2 turned out to be critical. The plan was to use it as a lightweight Linux environment for running MCP servers and GPU inference workloads that didn’t need a full VM. Running vLLM directly in WSL2 with CUDA passthrough to the RTX 5090 is genuinely one of those things that sounds like it shouldn’t work as well as it does.
The VM Strategy
Rather than one monolithic VM trying to do everything (the homelab equivalent of microservices trauma), the plan from day one was purpose-built VMs:
| VM | Purpose | The One-Liner |
|---|---|---|
| KaliLinux | Security scanning | Finds problems you didn’t know you had |
| UbuntuClaw | AI assistant + local inference | The one that texts you |
| DebIdentity | Identity, PKI, secrets | The bouncer |
| DebApps | Home services | Everything else |
Each VM gets its own VLAN, its own service account, and its own reason to exist. This makes the network topology slightly more complex and the documentation requirements significantly more annoying, both of which are signs you’re doing it right.
The Network Foundation
REX doesn’t sit in isolation. The broader lab runs on a Juniper EX3300 core switch (because enterprise switches show up on eBay for less than you’d expect, and the CLI is deeply satisfying), a pfSense firewall handling routing between six VLANs, and an Aruba wireless controller for the WiFi estate.
The VLAN breakdown:
- 172.16.50.x — VM workloads (KaliLinux, UbuntuClaw, DebIdentity, DebApps)
- 172.16.100.x — Infrastructure (NAS, switches, wireless controller)
- 172.16.250.x — Firewall and routing
Synology NAS sits at 172.16.100.100 and acts as the primary DNS server for sdx.local, which is the internal domain everything lives under. The NAS also handles backups — F: drive syncs to Synology nightly, Synology syncs to Google Drive, completing a 3-2-1 backup chain that lets me sleep without thinking about disk failure statistics.
The Use Case: Running AI Workloads Without Paying Cloud Rent
The machine justification that actually held up: the RTX 5090 runs local LLM inference at a quality level that would cost serious money in API calls if done at cloud rates. Once the infrastructure is built, the marginal cost of running a query against a local Gemma 26B model is essentially the electricity draw of the GPU — roughly $0.003 per hour of active inference on Australian residential rates.
At the volume of queries an active AI lab generates, that math gets interesting quickly. The upfront hardware investment starts looking less like an indulgence and more like a capital expenditure with a calculable payback period.
(I did not do this calculation before buying the hardware. But I did do it afterwards, which is almost the same thing.)
What Came Next
REX was the foundation, but a powerful machine sitting on a flat network with no identity management, no internal TLS, and no security posture isn’t a lab — it’s an expensive desktop. The next step was turning it into something you could trust: a network you understood, VMs that knew who they were talking to, and a PKI so the certificates stopped being self-signed afterthoughts.
That story starts with a Juniper switch, a pfSense firewall, and an uncomfortable amount of time reading RFC 1918.