
Agentic AI Workflows Explained: Patterns, Infrastructure, and GPU Requirements
Agentic workflows plan, loop, and burst differently than a single model call — here's what that means for the infrastructure underneath.
Blog
Our new Serverless CPU offering lets you launch high-performance containers without GPUs, perfect for lighter workloads, dev tasks, and automation.

We are thrilled to introduce the latest addition to the Runpod platform: Serverless CPU. This feature allows you to create high-performance VM containers with up to 3.75 GHz deviated cores, DDR5 memory, and NVME SSD storage.
With Serverless CPU, you have the flexibility to choose between Compute-Optimized or General Purpose CPUs and various configurations to suit your specific needs. Whether you require high compute power for intensive tasks or a balanced setup for general purposes, we've got you covered.
Getting Started:
Why Choose Serverless CPU over Serverless GPU?
While GPUs are well-known for their exceptional performance in parallel processing tasks, such as deep learning and complex computations, there are scenarios where CPUs are more suitable. Here are a few reasons why you might choose Serverless CPU over Serverless GPU:
Embrace the power of Runpod's Serverless CPU and elevate your application's performance today!
For a step-by-step guide on how to get started, check out our tutorial: Run an Ollama Server on a Runpod CPU.
Start Up a CPU Serverless Endpoint
Author profile: Brendan McKeag
Blog Posts

Agentic workflows plan, loop, and burst differently than a single model call — here's what that means for the infrastructure underneath.

What eleven teams built at the Runpod Flash Hack Day, and the three demos that took home the top prizes.

We tested four models across sixteen workload profiles. Here's exactly what we measured and how.