# Distributed with Diverse Hardware Support Cerebrum lets developers build and deploy large-scale AI Agents, leveraging thousands of AI Models (LLMs, Visual Models, etc.) by using a geographically distributed network. * **Simplified Development and Deployment:** Leveraging Nomad and specialized libraries, Cerebrum streamlines the development and deployment of compute-heavy across a massive grid of Model Host Computers. * **Broad Hardware Compatibility**: Cerebrum Cloud will support a wide range of compute hardware including NVIDIA, AMD Ryzen series for GPUs and Intel, AMD, Apple M2 with Neural Engine for CPUs * **Minimum Hardware Requirements:** To participate in the Beta network as a Model Host Computer, your system should have: * 8 GB or more of RAM * Nvidia System Support for Beta Release * Windows or Linux operating system * At least 500 GB of free disk space * Reliable internet connection with download speeds exceeding 100 Mbps, upload speeds exceeding 20 Mbps, and ping below 60ms to our Head Node. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.cerebrum.dev/cerebrum/technology-stack/distributed-with-diverse-hardware-support.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.