techblog– category –
-
Is an LLM API All You Need? A Fresh Look at Cloud GPUs in the Age of AI Agents and Powerful Open Models
API or cloud GPUs? What self-hosting open LLMs really buys you in the agent era. -
Turning the Community-Built Inference Engine “Strata” into a Single-GPU Inference Appliance
IntroductionQwen3.8-Flash-Next is a model that delivers response quality good enough that I'd almost call it a next-generation model that has already reached a certain level of completion. Because of that, quite a few people want to get ... -
AI Agent Development for Engineers: Architecture, Frameworks, and Cloud Infrastructure Choices
Learn how to build AI agents: architecture patterns, popular frameworks, and cloud infrastructure choices explained for engineers.
1