llama.cpp CUDA on nvidia-quadro-rtx-6000: Llama-2-7B Q4_0 FA-on tg128 decode tok/s (scoreboard #15013)

COMMUNITY-SCOREBOARD (llama.cpp discussion #15013, maintainer-curated). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 1. llama-bench default -r 5 repeats, mean reported (the +/- std is in the source row, not stored). Single GPU, per-request batch 1, NOT an aggregate across concurrent requests. Prompt length is the bench default for the tg test (the scored quantity is the 128 generated tokens). Re-read of the discussion page on 2026-10-16.

Quadro RTX 6000, 24 GB / GDDR6 / 384 bit, build 1e74897, reporter @Hedede. Turing TU102, not the RTX 6000 Ada and not the RTX PRO 6000 Blackwell. Maintainer-verified row. tg128 is the bandwidth-bound cell of the pair.