Runpod Blog.

Roleplay is one of AI's fastest-growing use cases. This guide walks you through building compelling, consistent TavernAI characters for immersive interactions.

Large language models like Guanaco 65B can run on Runpod with the right optimizations. Learn how to handle quantization, memory, and GPU sizing.

New 8k context models from TheBloke—like WizardLM, Vicuna, and Manticore—allow longer, more immersive text generation in Oobabooga. With more room for character memory and story progression, these models enhance AI storytelling.

Starting with runpod-python 0.10.0, you can launch a local API server for testing your worker handler using --rp_serve_api. This feature improves the development workflow by letting you simulate interactive API requests before deploying to serverless.

Use the VS Code Server template on Runpod to connect your local VS Code editor to a GPU-powered development pod, offering a seamless remote dev experience with full VS Code functionality.

Unlock seamless coding with the VS Code Server template on RunPod. Learn how to connect, code, and iterate remotely with local-like speed and responsiveness.

Learn how to use Runpod's new Savings Plans to save up to 20% on Secure Cloud pods with monthly or quarterly commitments—ideal for users with high GPU workloads.