llama.cpp ROCm on RX 7900 XTX: Llama-2-7B Q4_0 FA-off tg128 (#15021)
167.11 tok/s (tg128, per-request, batch 1)
Fields
id
benchmarks/llamacpp-rocm-7900xtx-llama27b-q40-nofa-tg128Metric
decode_tok_s
Value
167.11
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). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 0. AMD Radeon RX 7900 XTX (24 GB / GDDR6 / 384 bit). Build commit 2f0c2db, reporter @Diablo-D3. Mean +/- std (±0.50). Single-GPU run per thread rules. Per-request batch-1, NOT aggregate.
Measured by
third_party
Reproducible
yes
notes
Maintainer-verified scoreboard row from #15021. Identical model/test/flags across all GPUs. tg128 = decode, pp512 = prompt processing. 960 GB/s; the consumer ROCm decode leader on this board.
Notes
Maintainer-verified scoreboard row from #15021. Identical model/test/flags across all GPUs. tg128 = decode, pp512 = prompt processing. 960 GB/s; the consumer ROCm decode leader on this board.