llama.cpp ROCm on RX 6900 XT 16GB: Llama-2-7B Q4_0 FA-on tg128 decode tok/s
85.04 tok/s (tg128, per-request, batch 1)
Fields
id
benchmarks/llamacpp-rocm-rx6900xt-llama27b-q40-fa-tg128Metric
decode_tok_s
Value
85.04
Unit
tok/s (tg128, 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 6900 XT 16GB. Build commit a972fae, reporter @notgood. 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.
Notes
Paired with the other row from the same run.