Download from Hugging Face
Bring public weights and repos (or with your token) into node storage. Download queues, verification, and versions available from the panel.
Open catalog · Hugging Face
Xeretron lets you download models from Hugging Face and experiment openly from the panel to use them however you want — on your node, under your control, without being locked to the official catalog alone.
Model freedom
Omega, Titan, Turbo, and Developer are ready-to-run brains. The panel also opens the door to Hugging Face so you can explore, compare, and run what you need.
Bring public weights and repos (or with your token) into node storage. Download queues, verification, and versions available from the panel.
Try quantizations, prompts, agents, and workloads without asking a cloud provider for permission. Iterate locally until you find the model that fits.
Chat, CodiiX, APIs, research, demos, or internal production: you decide what the model is for in your Xeretron environment.
The same console that manages GPUs, queues, and runtimes: downloads, weights, and which models are ready to serve — no improvised SSH.
When the model is ready, you consume it like the rest of the Xeretron stack: tools, agents, and apps point to the same local endpoint.
Each HF repo carries its license (MIT, Apache, Community…). Xeretron facilitates download; you are responsible for honoring the terms of the model you choose.
Typical flow
The panel connects the open hub to the node runtime. You pick the repo; Xeretron handles the queue, storage, and making it servable.
Next step
Download. Experiment. Use the model your way — locally, with Xeretron.