A private inference bench for principals who already think in unit cost. Volume stays in the room. Outside intelligence is reserved for decisions that earn it.
Assayed July 2026. Capacity is indicative and set per engagement. This bench takes a small number of houses, not a queue.
MEG Z690 UNIFY. A heatsink 990 PRO on the CPU’s own PCIe root — full 16 GT/s ×4 — and that drive is also the system volume. Not a hub. Not a laptop SSD asked to play server.
Large in-house models run here, including a heavyweight reviewer on i7. How they are packed is craft. That they run on owned metal is the point.
Link state measured 30 July 2026. Board MS-7D28.
The commercial question is not peak theatre. It is how long real bulk takes when the path is local and the bill is electricity.
Reproducible on request — dates, not adjectives.
Bulk drafts fan across the mesh. A heavyweight reviewer sits on i7. The daily seat keeps a strong midweight for orchestration. Outside models only where the work earns them.
Rates: heavy reviewer ~28 tok/s on i7 (Vulkan, dated 17 Jul). Draft tier ~21–40 tok/s per node. Real-prompt bulk classify ~4.09 items/s mesh-wide. Swarm concurrency knee ~6. Model names and packing method on enquiry.