Fleet Management

One model per machine, or one model across many.

Cascadia finds the machines with room and places the model for you: a copy on each, or one model split across several. Add machines with a link, see usage, and any change that fails rolls back on its own.

One 35B model split across two machines, and a whole model on each of the other six.

API endpoint

3 models on 8 machines

Too big for one machine?
Cascadia splits it for you.

01

Pick a model.

Fleet Management checks it against every machine’s free memory.

Qwen2.5 7B

7B · int4

4.5 GB

Phi-4 14B

14B · int4

8.1 GB

Qwen2.5 32B

32B · int4

17.8 GB

Qwen3.6 35B

35B MoE · int4

21 GB

largest machine · 18.4 GB free

02

Cascadia splits it.

It picks the machines with the most room. Prefer to choose them yourself? Switch to manual.

Qwen3.6 35B

35B paramsMoE · int440 layers21 GB

L1

L20

L21

L40

stage 1 · L1–20

lab-05

10.5 of 18.4 GB

stage 2 · L21–40

lab-06

10.5 of 17.9 GB

03

Roll it out.

Stages commit together, then one endpoint serves it.

Deploy Qwen3.6 35B

Download

Load

Staged

Commit

Verify

holding 1:42

Serving

lab-05

stage 1

committed

lab-06

stage 2

committed

API endpoint

healthy

http://198.51.100.15:9110/v1

qwen3.6-35b

verifying

Fits on one machine?
Run it there, on OpenVINO.

Built with Intel for the AI PCs you already own. Cascadia runs every model on OpenVINO, Intel’s own AI runtime. Models are compressed to fit an office PC’s memory and run on the processor, graphics and NPU built into Intel Core Ultra.

~30 tok/s

An 8B model on one Intel AI PC, with speculative decoding.

14B on one PC

4-bit weights fit a 14B model in a 32 GB office machine.

CPU, GPU and NPU

OpenVINO uses every engine in the chip, including the NPU most software leaves idle.

Hand the install to whoever sits at the machine.

IT doesn’t have to touch the computer. Send the person a link; they click one button; you watch each step land.

Nothing to unblock in the inbox

No files or commands in the email, so it clears mail filters.

One link, one machine

Each link adds a single device and expires in seven days.

A whole room at once

Doing it yourself? One batch installer enrols up to 500 machines.

See what the fleet did, and what needs you.

Tokens, requests and success rate over any range, by model, device or API token, with a year of daily activity. Status checks the fleet every 15 seconds and lists what needs attention.

automatic rollback

If a change fails, it rolls back on its own.

pipelines

A pipeline goes live whole, or not at all.

If any stage fails, every machine reverts.

model switches

If a new model fails, the old one comes back.

The previous model stays on disk, ready to take over.

updates

A failed app update rolls back.

Fleet Management keeps a new version only if it passes a self-test.

cascadia desktop

Then put it to work at every desk.

Desktop is the private AI app for every employee. It runs on the models you deploy here, and nothing anyone types leaves your network.

Cascadia Desktop: a chat summarising the termination clauses in an MSA, answered by Llama 3.1 8B, with the tray menu open.

FAQ

Questions, answered.

Put your first model on the fleet.

We set up a pilot on machines you already own, and your team deploys from Fleet Management from the first day.

See it run on hardware like yours.

Book a demo

Check the engineering first.

See our research