Local models
Find a model on Hugging Face, download it to any of your Macs, and start it when you choose.
Full model lifecycle
Search Hugging Face
Search by family, size, task, and quantization type, right from the Models page.
Download with progress
Live progress for every download, including gated models you have access to.
Move and delete
Copy a model to another Mac, move it to another disk, or delete it, from the same list.
Deploy to any Mac
Start a model on any Mac in your cluster, with no SSH or config files. It only starts when you launch it.
Copy between Macs
Send a model to another Mac, at 5+ GB/s over Thunderbolt 5 RDMA.
Pluggable storage
Storage backends are auto-discovered at boot. Local SSD, NAS mounts, external Thunderbolt drives — anything the OS can see, the pipeline can use. New volumes appear in the model inventory automatically. No config changes needed.
Same principle applies to compute. When a new node joins the cluster and asmi comes online, its storage and GPU capacity become available to the pipeline instantly. Remove a drive or a node and the inventory updates within one poll cycle.