llama.cpp ROCm on RX 9060 XT 16GB: Llama-2-7B Q4_0 FA-on pp512 prefill tok/s
1479.27 tok/s (pp512, per-request, batch 1)
Fields
id
benchmarks/llamacpp-rocm-rx9060xt-llama27b-q40-fa-pp512Metric
prefill_tok_s
Value
1,479.27
Unit
tok/s (pp512, per-request, batch 1)
Model
llama-2-7b.Q4_0.gguf (TheBloke, 3.56 GiB, 6.74B params)
Methodology
COMMUNITY-SCOREBOARD (llama.cpp discussion #15021, maintainer-curated ROCm backend). llama-bench llama-2-7b.Q4_0.gguf, ngl=99, -fa 1. RX 9060 XT 16GB. Build commit a0e13dc, reporter @lcy0321. llama-bench default repeats, mean. Single device, per-request batch-1, NOT aggregate.
Measured by
third_party
Reproducible
yes
notes
Paired with the other row from the same run. Scoreboard prints a 256-bit bus; the reporter corrected it to 128-bit in the same thread.
Notes
Paired with the other row from the same run. Scoreboard prints a 256-bit bus; the reporter corrected it to 128-bit in the same thread.