Geerling llama.cpp Vulkan on rtx3080ti (pc host): llama-2-13b Q4_K_M pp4096+tg128 756.69 tok/s
756.69 tok/s (pp4096+tg128)
Fields
id
benchmarks/geerling-vulkan-rtx3080ti-pc-llama-2-13b-q4km-pp4096-tg128Metric
tps_aggregate
Value
756.69
Unit
tok/s (pp4096+tg128)
Model
llama-2-13b.Q4_K_M.gguf (7.33 GiB, 13.02 B params)
Methodology
THIRD-PARTY MEASURED (Jeff Geerling, geerlingguy/ai-benchmarks). llama.cpp build d82b7a7c1 (7193), backend Vulkan, default llama-bench flags (ngl 99). Host: Intel Core Ultra 265K, 64GB DDR5, Ubuntu 25.10. Model file size 7.33 GiB, 13.02 B params, Q4_K_M. llama-bench combined pp4096+tg128 figure: one prompt of 4096 tokens followed by 128 generated tokens, reported as a single tok/s. This is neither pure prefill nor pure decode; stored as tps_aggregate with concurrency 1. Whole-system wall power during the run 363.7 W (node scope, not device).
Measured by
third_party
Reproducible
yes
Mean power (W)
363.7
Power scope
node
Thermal state
unknown
notes
Source issue prints the llama-bench mean and the +/- spread; the stored value is the mean. The Pi-host rows are the same physical GPU on a PCIe-constrained host, so they are not a card ceiling.
Notes
Source issue prints the llama-bench mean and the +/- spread; the stored value is the mean. The Pi-host rows are the same physical GPU on a PCIe-constrained host, so they are not a card ceiling.