Skip to the card

Card 643 of 9752026-09-23 issue

Observed arrival · 2026-09-23

EcoCompute measures the energy cost of LLM quantization

quantenergy.dev Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

An open benchmark protocol for measuring how LLM quantization affects GPU energy use, with data, runnable tools, and a public coverage matrix.

Landing page captured for the 2026-09-23 issue.
For
Researchers and engineers comparing LLM inference energy
Worth noticing
Both the container and free Colab notebook emit the same energy.json format; contributors preview results in-browser before opening a GitHub issue.

Field notes

The protocol fixes decoding at batch size one and 256 tokens, samples NVML power at 10 Hz, and limits its figures to GPU-package draw rather than whole-system energy. A free Colab notebook and an MLCube-compatible container produce the same schema-validated file, which contributors can inspect against the published curve before preparing a GitHub issue. The page also distinguishes its main dataset's reported n=2 from a deeper RTX 4090 set with n=1 per configuration.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use
HumanPersonal, local, civic, or handmade

One card from the complete issue

Racing the Bulldozers

362,307 arrived 1,000 judged 975 catalogued Enter the complete issue
quantenergy.dev

Landing page observed 2026-09-23. The live site may have changed.