System Requirements

Supported platforms

OptimaGPT runs on Windows, Linux, and macOS. All three components — Gateway, Node, and the desktop chat application — are supported on all platforms.

Platform	Architecture
Windows	x86-64, ARM64
Linux	x86-64, ARM64
macOS	Apple Silicon (ARM64) only

macOS on Intel is not supported.

OptimaGateway

The Gateway is a lightweight server process with modest resource requirements.

	Minimum
CPU	2-core, 64-bit
RAM	2 GB
Disk	10 GB
Network	A fixed IP address or hostname reachable by users and Node machines

OptimaNode

Node requirements vary significantly depending on the AI models you intend to run. Model files range in size from a few gigabytes to over 40 GB, and loading them requires either sufficient system RAM or a GPU with adequate VRAM.

	Minimum	Recommended
CPU	4-core, 64-bit	8+ cores
RAM	8 GB	32 GB or more, depending on model size
GPU	Not required	Dedicated GPU with 8 GB+ VRAM, strongly recommended
Disk	20 GB + model storage	SSD with 100 GB+ available

GPU acceleration: Running models on a GPU is significantly faster than CPU inference. For production use or any model larger than 7 billion parameters, a GPU is strongly recommended. Both NVIDIA and AMD GPUs are supported.

RAM and model size: If running on CPU only, the system must have enough RAM to hold the model in memory. As a rough guide, a 7-billion parameter model in Q4 quantisation requires approximately 4–5 GB. A 70-billion parameter model in Q4 requires approximately 40 GB. Embedding models are generally much smaller.

OptimaGPT Desktop App

The desktop application runs on the same platforms and architectures as the Gateway and Node. Its own hardware requirements are minimal — any machine capable of running the operating system will run the desktop app.