genie.locker Open a locker

Private model hosting

Your own model.
Private, sandboxed,
yours.

A language model that belongs to you alone. It remembers your work, runs on disposable hardware, and no one else can read it. Not an API key on someone else's model — a locker with your model inside.

validation · RTX A6000 · 2026-07-28
$ parity --atol 0 --ctx 8192
  PASS  output identical to full-memory run

$ memory
  full        17.49 GB
  locker      5.84 GB   -66.6%

$ throughput --batch 16
  aggregate   58.6 tok/s
  per locker  3.66 tok/s
  scaling     13.72x

Unedited output. Method below.

0.00
difference vs a full-memory run
66.6%
less memory, worst case measured
13.72×
throughput scaling, 16 lockers
26s
cold start to a live locker

You don't own anything you're using today.

Every prompt you send goes to a model someone else controls, trained on terms you didn't set, changed without warning, and retired when it suits them. Your context lives in their logs. Your work improves their product.

The model changes under you

A silent update rewrites behaviour you'd tuned around.

Your locker is pinned. The weights are yours. Nothing changes unless you change it.

Your context isn't private

Everything you've told it sits in someone else's system.

Sealed storage. Your model and memory live in your locker, encrypted at rest.

Owning one means owning a GPU

Self-hosting has meant buying hardware and babysitting it.

Hardware is disposable. We hold your model in a third of the memory, so a rented card runs it for cents. The machine dies; the locker persists.

Two kinds of privacy.

The difference is where the wall sits: cryptographic, or physical. Both keep your model and memory yours. One shares a machine; one doesn't share anything.

Shared Engine

Recommended

Your model and memory are yours and sealed. The engine serving them is shared with other lockers, isolated cryptographically rather than by machine.

$39/month
  • Your weights, pinned and private
  • Encrypted memory that grows with you
  • Always warm, ~3.7 tokens/sec
  • Pay by card or USDC
Open a shared locker

Sovereign

Isolated

Your own process on your own card. Nothing else runs beside it. The wall is physical, not cryptographic — for work where that distinction is the whole point.

$399/month
  • Everything in Shared
  • Dedicated GPU, no co-tenants
  • Full speed, ~4.2 tokens/sec
  • Signed receipt for every session
Open a sovereign locker

Speeds are measured, not projected. A locker is built for sustained and background work — it is deliberately not the fastest way to get a token, it is the most private.

No testimonials. Measurements.

Genie is new and has no customers yet, so there is nothing honest to quote. Here is what we measured instead, on rented hardware, with the method stated.

Correctness

Your compressed model produces output identical to the uncompressed one — not close, identical, to the last decimal, verified at both short and long context.

atol 0 · ctx 2048 & 8192 · PASS
Memory

A model needing 17.5 GB runs in 5.8 GB. Savings shrink as context grows, so we quote the worst case, not the best.

73.5% → 66.6% · 7B · RTX A6000
Density

Sixteen lockers on one card deliver 13.72× the throughput of one, each losing only 14%. That result is why Shared costs $39.

58.6 tok/s aggregate · batch 16

What we don't claim

A locker is not fast. Around 4 tokens per second is a fraction of what a commodity API gives you, and if speed is what you need, buy speed instead. We have no paying customers and no uptime history. Shared isolates cryptographically, not physically — if your threat model rules that out, Sovereign is the only honest answer. And the hardware underneath is rented, so we depend on suppliers we do not own.

Questions

What does "grows with you" actually mean? +

Your locker keeps what you put in it — your documents, your corrections, the way you want things phrased — as data that belongs to your model, not to a chat history on someone's server. It carries forward across every session and every machine.

How is Shared private if the engine is shared? +

Your weights and memory are encrypted and only decrypted for your requests. Other lockers on the same machine can't address them. It is the same boundary your bank uses between accounts on one system — strong, but a software boundary. Sovereign removes the shared machine entirely, and we'd rather state the difference plainly than blur it.

Why is it slower than the model I use now? +

Because it fits in a third of the memory. We stream your model through cheap hardware instead of parking it on expensive hardware, which is what makes a private model cost $39 rather than $600. The output is identical — it simply arrives at reading pace.

What happens if you shut down? +

You export the locker and run it yourself. It's an open-weights model plus your own data in a documented format — no proprietary lock. That's what makes it yours rather than rented.

Can I pay without a card? +

Yes. USDC on Base, per session or per month, no account required for the pay-per-use tier. Cards work too if you'd rather.

Stop renting someone else's mind.

Open a locker in under a minute. Export it whenever you like.

No card required to start · Export anytime