Evidence · benchmarks · download

Proof you can open — no NDA required for the headlines.

Every material number on this site points here: public packs, measured tables, and demo binaries.

Benchmarks

Results from public LuxiDemo evidence on H100 hardware (2026-07-11). Open any pack to inspect methods and raw traces.

7B-class TRADE — energy & throughput

Hardware: 1× NVIDIA H100 NVL · 28-layer stack · public pack.

Sequence length Tokens / sec Joules / token Median power (W) Notes
5~443.560 ± 0.005~156Short-burst reference
32~221Throughput sweep
64~359Throughput sweep
128~4030.630 ± 0.002~254Primary result
256~464~0.604~280Longer context
512~493Throughput sweep

Primary multi-run at sequence length 128. Source: evidence/h100-7b-class-TRADE/

Head-to-head with a Flash baseline

12 layers · sequence 1024 · h=768 · ~10 s each side.

MetricTRADE 12LPyTorch + Flash 12LRatio
Median power (W)177.2176.4~1.0×
ms / stack forward74.323.90TRADE 19.1× slower
Prefill tok/s13778262859PT 19.1× higher
Joules / token0.01290.0007TRADE 19.2× higher

h100-stack12-H2H — we publish where a standard baseline wins on this shape.

Long-context memory

Sequence lengthWaller state (MB)Dense scores (MB)Reduction
1,0240.528.416×
4,0962.113464×
8,1924.2537128×
32,76816.84,295256×

Memory scales near-linearly vs dense O(N²). Pack →

Download

Public demo builds for the expression/receipt path. Demo only — not production inference. Energy claims live in the packs above, not only inside these binaries.

Open latest release →

LuxiEdge Lite / Demo

macOS ARM, Linux x86 (CPU/GPU), Linux ARM, Windows — from the public release channel.

Quick start

chmod +x luxiedge-*-macos-arm64
./luxiedge-*-macos-arm64 --port 9090

curl -X POST http://localhost:9090/evaluate \
  -H "Content-Type: application/json" \
  -d '{"expr":"sin(x)","values":[0.5,1.0],"precision":"f32"}'
Demo binaries may expire. Full operator sets require a license — contact.