Local AI Server Deployment

Deploy a RegScale AI Inference Server locally to support RegML functionality. This option is for air-gapped or private infrastructure environments. Our SaaS platform includes this by default for cloud users.

System Requirements

Host Requirements

• Docker Engine installed
• NVIDIA GPU with latest drivers supporting CUDA ≥ 12.8
• Linux with NVIDIA Container Toolkit
• Windows is not recommended, but GPU containers can be tested via Docker Desktop GPU Support

Hardware Requirements

• GPU: 24GB+ VRAM
• RAM: 32GB
• CPU: 16+ cores
• Storage: 50GB+ Free

---

Model Download

We provide a custom version of Microsoft’s Phi-4 model.