llama.cpp CUDA on nvidia-rtx-4090-d: Llama-2-7B Q4_0 FA-on pp512 prefill 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, prompt length 512 tokens, no generation. llama-bench default -r 5 repeats, mean reported. Single GPU, one request, NOT an aggregate across concurrent requests. pp512 tracks compute rather than bandwidth. Re-read of the discussion page on 2026-10-16.

RTX 4090 D, build 79c1160, reporter @autonomous-ai-lab. Prefill cell of the same row as the tg128 record for this card.