llama.cpp ROCm RX Vega 64 llama-2-7b Q4_0 pp512 FA
153.17 tok/s (pp512)
Fields
id
benchmarks/llamacpp-scoreboard-radeon-rx-vega-64-fa-pp512Metric
prefill_tok_s
Value
153.17
Unit
tok/s (pp512)
Model
llama-2-7b.Q4_0.gguf (ggml-org, 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 (ggml-org, 3.56 GiB, 6.74B params), pp512 and tg128, n_gpu_layers 99, batch 1, full GPU offload, ROCm. Per-request batch-1, not an aggregate across concurrent requests. Flash attention on (-fa 1). Build ec428b0, reporter @davispuh. Printed mean 153.17. Re-read of the discussion page on 2026-10-17.
Measured by
third_party
Reproducible
yes
notes
RX Vega 64, 8 GB / HBM2 / 2048 bit, build ec428b0, reporter @davispuh. prompt processing cell.
Notes
RX Vega 64, 8 GB / HBM2 / 2048 bit, build ec428b0, reporter @davispuh. prompt processing cell.