# Lumai deploys Iris optical servers in ARIA’s £50M Scaling Inference Lab

Digest AI · Hardware & Compute · published 2026-11-03T16:50:58Z

Canonical: https://digestai.news/story/lumai-deploys-iris-optical-servers-in-arias-50m-scaling-inference-lab

## Summary

The lab, run by CommonAI CIC, will use Lumai’s Iris servers as its first optical-compute platform to evaluate rack-scale integration in a commercial data-center environment. This follows the April launch of Iris Nova, which supports Llama models with 8 billion and 70 billion parameters and is available for data-center evaluation under standard rack infrastructure and air cooling.

Lumai’s hybrid optical-digital architecture targets dense matrix operations in AI inference, aiming to execute calculations in parallel via light propagation rather than transistor switching. The company claims potential power savings of up to 90% and total cost of ownership reductions to around one-tenth of conventional GPUs, though these figures are unconfirmed by independent validation. The lab’s structured pilots—each incorporating unproven tech into deployable systems—will compare full-system performance against commercial alternatives, with a new rack planned every six months. Lumai’s CEO, Xianxin Guo, called the ARIA deployment a critical step to prove real-world readiness.

## Key points

- Lumai’s Iris servers tested in ARIA’s £50M Scaling Inference Lab for rack-scale integration
- Iris Nova supports Llama models with 8B and 70B parameters, available for data-center evaluation
- Lumai claims up to 90% power savings but lacks independent validation for full-system gains

## Why it matters

If Lumai’s optical servers deliver on claims, they could offer a power-efficient alternative to GPUs for AI inference, addressing UK’s limited power budgets for domestic AI growth. The lab’s real-world testing may validate or refute the tech’s scalability beyond benchmarks.

## Sources

1. [ARIA Selects Lumai Optical Servers for Rack-Scale AI Inference Testing](https://unite.ai/aria-lumai-optical-servers-ai-inference-testing) (Unite.AI, 2026-11-03)

## Cite

Digest AI, "Lumai deploys Iris optical servers in ARIA’s £50M Scaling Inference Lab", 3 November 2026, https://digestai.news/story/lumai-deploys-iris-optical-servers-in-arias-50m-scaling-inference-lab

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/lumai-deploys-iris-optical-servers-in-arias-50m-scaling-inference-lab.json