Cascadia local
Run local models fully offline on the Intel hardware you own, from one machine to several. No cloud, no subscription, nothing leaving your network.
why local
Private by default
Your prompts and documents never leave your devices.
Yours to own
Runs on hardware you bought. No account required.
No subscription
No per-token bill. Generate as much as you like.
Works offline
On a plane, in a SCIF, off the grid. No signal needed.

what your hardware can run
two versions
Start free on one machine, or run it across your company with central control.
Cascadia Local
Capable models on the Intel hardware you own, fully offline.
Cascadia Enterprise
Private AI infrastructure across the Intel machines you already own, managed from one place.
| Feature | Cascadia Local | Cascadia Enterprise |
|---|---|---|
| Deployment | Download and install | Deployed with our team, first model in under a week |
| Price | Free for individuals | Licensed per device, never per token |
| Runs on | One Intel PC, or a few on your network | Your whole fleet of Intel machines |
| Largest model | Up to ~14B on one 32 GB PC, larger by pooling a few | 1T-class models on hardware you own |
| Users | Single-user optimized | Shared across your company, with admin roles |
| Support | Self-serve | Supported by our team |
| Member roles, invites and API tokens | Not included | |
| Audit log of admin actions | Not included |
running a team?
Local already pools the Intel machines on your network. Cascadia Enterprise adds what a team needs on top: roles and invites, an audit log of admin actions, and central control, up to a 1T model, on-prem.
Download it and run capable local models on the Intel hardware you already own.
Free for individuals
DownloadDeploying across an organization?
Talk to our team