System Requirements
Hardware and OS requirements for running CrestBid locally.
CrestBid performs AI inference locally, so performance depends mostly on your GPU. It runs on Windows, macOS, and Linux.
For fully local, private AI
- NVIDIA GPU — an RTX-class card is recommended (the installer offers model sizes to match your VRAM)
- 16 GB system RAM (32 GB recommended)
- ~50 GB free disk space for the application and AI models (more for large knowledge bases)
- Windows 11 (the installer sets up WSL2 and Docker for you) or a modern Linux distribution
- NVMe SSD recommended for fast knowledge-base indexing
No NVIDIA GPU? (including Macs)
Machines without an NVIDIA GPU — including all Macs — run CrestBid in cloud-model mode: the platform installs and works the same, but inference is served by a model provider you configure, or by a GPU machine elsewhere on your own network (remote model mode). It works great for trying the product out; for fully-local, private AI, use a Windows or Linux PC with an NVIDIA RTX graphics card.
When a cloud model provider is configured, prompts leave your machine for that provider. For zero data exposure, run local models on an NVIDIA GPU — or point CrestBid at a GPU host inside your own network.