postl.ai — a one-person AI research lab, self-hosted in an attic in the Piestingtal. Fully encrypted. Zero cloud.
The fleet
Each tile is a real system — the bigger the tile, the bigger the iron. 184 cores / 368 threads, 1.3+ TB RAM, five NVIDIA cards totalling 44,544 GPU cores & 90 GB VRAM, 120 TB of encrypted storage. Tap a tile to open it up.
The minds
One uncensored flagship LLM plus the full generative stack — text, image and video, the whole ComfyUI pipeline, served entirely on the machines above. No tokens, no frames leave the valley. Tap the orb — it'll say something else.
demo · uncensored · full Q8 precision
~4 min per clip · the pretty one
~12 s per clip · the fast one
~10 images/min · the sharp one
~30 images/min · batch all day
▸ full model fleet, benchmarks & roadmap: /models
postl.ai is the front door of a fully self-hosted machine hall — in an attic in the Piestingtal. Owned hardware, encrypted end to end, no cloud in the loop.
t.postl@pm.meps: there's usually a spare U in the rack. the rack likes company.