21:15
2026-09-15
gist.github.com
ai-infrastructure
Measure how much local LLM speed your Mac loses to heat over 30 minutes. Declares its definitions for burst, retention and onset so your numbers are comparable to someone else's.
A developer released sustained_bench.py, an open-source Python script that measures how much local LLM inference throughput on Apple silicon decays over a 30-minute sustained run due to thermal thrott…