Three audiences · one mission

AI that uses less electricity — and proves it.

LuxiEdge is built for quant research, AI data centers, and a public that can drive change by sharing the energy story and asking providers why they are not measuring and cutting waste.

~403
Tokens per second
0.63
Joules per token
~254 W
Power during the work
Full 28-layer stack
O(N)
Long-context memory scaling

Numbers from public multi-run benchmarks. Full methods and downloads: Proof.

A three-legged stool

Pick the path that fits you. Every path can end in shareable proof.

Quant & research

Determinism, audit trails, free-ride paths, long-context memory — for people who need methods, not slogans.

Science path →

AI & data centers

Power caps, density, measured joules-per-token under load, and a commercial path to evaluation.

Operator path →

We need your help

You don’t need a PhD. Share the energy story. Ask AI providers and data centers why they aren’t cutting waste.

Public path →

What we measure — honestly

On the public record

  • Full 28-layer 7B-class stack on H100
  • Multi-run throughput and energy per token
  • Supporting stack energy and free-ride tests
  • Long-context memory scaling (O(N) vs O(N²))

What we do not claim

  • Not a claim of chat-quality superiority over every model
  • Some standard stacks still win raw short-sequence speed
  • We differentiate on audit, memory scaling, and measured energy
  • Facility wall-plug power needs separate metering
We publish comparisons both ways. See the Proof page for packs, tables, and downloads.