llama.cpp ROCm on Radeon PRO V620 32GB: Llama-2-7B Q4_0 FA-on pp512 prefill tok/s
1256.86 tok/s (pp512, per-request, batch 1)
Fields
id
benchmarks/llamacpp-rocm-prov620-llama27b-q40-fa-pp512Metric
prefill_tok_s
Value
1,256.86
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. Radeon PRO V620 32GB. Build commit 5c0eb5e, reporter @samteezy. 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.