# Bentaus cuts AI token energy use by 30% with DriveNets fabric

> The NeoCloud runs AMD MI325X GPUs on DriveNets AI Fabric, saving power while keeping 97% of token throughput.

Oossa · 2026-11-12 · https://oossa.com/en/bentaus-cuts-ai-token-energy-use-by-30-with-drivenets-fabric

Bentaus, an energy‑first NeoCloud, teamed with DriveNets to deploy the DriveNets AI Fabric on a cluster of AMD Instinct MI325X GPUs. The joint solution uses Bentaus’ Ziani orchestration software to adjust GPU power in real time. According to the companies, the setup reduces energy per token by 30% and keeps 97% of token throughput, meaning only a 3% loss in speed. The architecture also claims about 5% higher overall throughput and a 12% faster time to the first token compared with publicly available results.

## The facts

- 30% less energy per token
- 97% token throughput (3% loss) on AMD Instinct MI325X GPUs

## Why it matters

Enterprises can run more AI work for less electricity, easing grid strain in regions with data‑center power limits.

## Sources & references

1. [Bentaus, an Energy-First NeoCloud, Deploys DriveNets High-Performance AI Fabric with AMD GPUs to Produce AI Tokens with 30% Less Energy](https://www.prnewswire.com/news-releases/bentaus-an-energy-first-neocloud-deploys-drivenets-high-performance-ai-fabric-with-amd-gpus-to-produce-ai-tokens-with-30-less-energy-302937017.html) – PR Newswire RSS, 2026-11-12

Last updated: 2026-11-12