• Recommended article: How to Quickly Assess the ROI of AI Implementation – Productive24AI at AI Summit 2025

    How can you quickly assess the business impact of AI implementation? It’s one of the toughest questions CEOs, CIOs, and CTOs face today. Low-code technology offers an answer - enabling organizations to design and test prototype applications equipped with AI assistants and agents, all within a single, integrated IT environment, in just a few days....

4 min.
TECHNOLOGY

How we ran a 744-billion-parameter AI model on our own GPUs and made it 36× faster

16 July 2026
Krzysztof Bender
How we ran a 744-billion-parameter AI model on our own GPUs and made it 36× faster
4 min.

From a crashing pod to 188 tokens per second: a hands-on story of self-hosting GLM-5.2 on vLLM, with the kind of problems you won't find in the tutorials. Short and to the point....