BENCHMARK
What this measures
llama.cpp pp512 measures LLM inference performance via llama_bench. Higher scores indicate better LLM inference throughput. We run this benchmark twice per device: once on AC and once unplugged. The BPR ratio (battery ÷ AC) appears in the rightmost column. This test contributes to the device's BPR score.
Read the full methodology for tool versions, run order, and exclusion rules.
No measurements yet
No products have been scored on llama.cpp pp512 yet. This page populates as new reviews are published. Check back after the next review ships, or read the methodology for what this benchmark captures.
How we test
View the GlitchTech methodology →