llama.cpp Vulkan on nvidia-tesla-p100: Llama-2-7B Q4_0 FA-on tg128 decode tok/s (scoreboard #10879)
66.48 tok/s (tg128, per-request, batch 1)
Fields
id
benchmarks/llamacpp-vulkan-tesla-p100-llama27b-q40-fa-tg128Metric
decode_tok_s
Value
66.48
Unit
tok/s (tg128, per-request, batch 1)
Model
llama-2-7b.Q4_0.gguf (ggml-org, 3.56 GiB, 6.74B params)
Methodology
COMMUNITY-SCOREBOARD (llama.cpp discussion #10879, Vulkan backend, maintainer-curated "Llama 2 7B, Q4_0, FA enabled" table). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 1. build eec1e33. tg128 is generation of 128 tokens, per-request batch 1, NOT an aggregate across concurrent requests. Re-read of the discussion page on 2026-10-17.
Measured by
third_party
Reproducible
yes
notes
Vulkan scoreboard row. tg128 is the bandwidth-bound cell of the pair. FA-on row; the no-FA sibling for this chip, where one exists, is a separate record.
Notes
Vulkan scoreboard row. tg128 is the bandwidth-bound cell of the pair. FA-on row; the no-FA sibling for this chip, where one exists, is a separate record.