Writing · Tag

#gpu-benchmarks

1 post tagged #gpu-benchmarks.

Aug 4, 20265 min read
Why Local LLM Benchmarks Need Power Data
A local LLM benchmark that reports only tokens per second hides the operating cost. My RTX 5090 run shows what power data adds.
#local-llm#gpu-benchmarks#ollama#5090-reports

The AI agent build notes

Real costs, real tools, no fluff. M-F when I ship, publish, or learn something worth sending.