llama.cpp Vulkan on Tesla M40: Llama-2-7B Q4_0 FA-off pp512 prefill tok/s (scoreboard #10879)
92.48 tok/s (pp512, per-request, batch 1)
Fields
id
benchmarks/llamacpp-vulkan-tesla-m40-llama27b-q40-nofa-pp512Metric
prefill_tok_s
Value
92.48
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 #10879, maintainer-curated). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 0. Tesla M40. Build commit b8372ee. 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 b8372ee.
Notes
Maintainer-curated scoreboard row from ggml-org/llama.cpp discussion #10879, non-FA table (llama-bench -fa 0). Build commit b8372ee.