Learn
How llmrun estimates memory, speed and quality, and where the numbers come from.
3 reference pages · updated Oct 24, 2026
How llmrun measures
The reference pages behind every number on the site.
How llmrun determines model requirements
How llmrun decides whether a GPU can run an LLM: VRAM, quantization, decode and prefill speed, time to first token and the S–F Fit scale.
6 grades, S to FUpdated Oct 14, 2026
How the llmrun Composite Score is built
How llmrun combines public LLM benchmarks into one open-ended Composite Score with Item Response Theory, a 90% range and per-skill scores.
One score with a 90% rangeUpdated Oct 24, 2026
Which benchmarks llmrun uses
A plain-English guide to the LLM benchmarks llmrun aggregates: what each one tests, how to read the scores, and open vs proprietary models.
4 sources, creditedUpdated Oct 17, 2026