Geerling llama.cpp Vulkan on rtx2080ti (pc host): tinyllama-11b Q4_K_M pp512 7389.30 tok/s
7389.3 tok/s (pp512)
Fields
id
benchmarks/geerling-vulkan-rtx2080ti-pc-tinyllama-11b-q4km-pp512Metric
prefill_tok_s
Value
7,389.3
Unit
tok/s (pp512)
Model
TinyLlama-1.1B-Chat Q4_K_M GGUF (528.14 MiB, 1.10 B params)
Methodology
THIRD-PARTY MEASURED (Jeff Geerling, geerlingguy/ai-benchmarks). llama.cpp build f9ec8858e (7474), backend Vulkan, default llama-bench flags (ngl 99). Host: Intel Core Ultra 265K, 64GB DDR5, Ubuntu 25.10. Model file size 528.14 MiB, 1.10 B params, Q4_K_M. prefill tok/s, prompt length 512, per-request, batch 1. NOT aggregate. Whole-system wall power during the run 290.5 W (node scope, not device).
Measured by
third_party
Reproducible
yes
Mean power (W)
290.5
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.