llama.cpp ROCm Radeon 880M llama-2-7b Q4_0 pp512 noFA
163.25 tok/s (pp512)
Fields
id
benchmarks/llamacpp-scoreboard-radeon-880m-nofa-pp512Metric
prefill_tok_s
Value
163.25
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 off (-fa 0). Build c55d53a, reporter @Hedede. Printed mean 163.25. Re-read of the discussion page on 2026-10-17.
Measured by
third_party
Reproducible
yes
notes
Radeon 880M, System Shared / DDR5, build c55d53a, reporter @Hedede. prompt processing cell.
Notes
Radeon 880M, System Shared / DDR5, build c55d53a, reporter @Hedede. prompt processing cell.