SofiaLLM Ops
Institutional LLM operations
Language models behind one OpenAI-compatible endpoint, with all your usage in one place.
Always-on models
One OpenAI-compatible endpoint for models that are always loaded. No allocation, no waiting.
Temporary inference on demandComing soon
Bring up a base or fine-tuned model on HPC GPUs and hold them only for the time you need.
Fine-tune and prove itComing soon
LoRA and QLoRA fine-tuning jobs, with evaluation runs and side-by-side comparison built in.
Universidad de Salamanca
Project SOFIA · CDTI–AEI
Sign in
Use the institutional Google account linked to your research group.
Continue with Google
Sign in with your institutional Google account.
API keys, GPU budgets and token quotas are attached to your account.
Usage is recorded per key, project and model.
Access is limited to enabled accounts. Contact a platform administrator if your group is not yet provisioned.
Terms of use · Data processing