llama.cpp Vulkan on Radeon AI Pro R9700: Llama-2-7B Q4_0 FA-off tg128 decode tok/s (scoreboard #10879)
145.67 tok/s (tg128, per-request, batch 1)
Fields
id
benchmarks/llamacpp-vulkan-r9700-llama27b-q40-nofa-tg128Metric
decode_tok_s
Value
145.67
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 #10879, maintainer-curated). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 0. Radeon AI Pro R9700. Build commit dd1ea52. llama-bench default repeats, mean. Single device. Per-request batch-1, NOT aggregate.
Measured by
third_party
Reproducible
yes
notes
Maintainer-curated scoreboard row from ggml-org/llama.cpp discussion #10879, non-FA table (llama-bench -fa 0). Build commit dd1ea52.
Notes
Maintainer-curated scoreboard row from ggml-org/llama.cpp discussion #10879, non-FA table (llama-bench -fa 0). Build commit dd1ea52.