llama.cpp Vulkan on intel-arc-b570: Llama-2-7B Q4_0 FA-off pp512 prefill tok/s (scoreboard #10879)
913.95 tok/s (pp512, batch 512)
Fields
id
benchmarks/llamacpp-vulkan-arc-b570-llama27b-q40-nofa-pp512Metric
prefill_tok_s
Value
913.95
Unit
tok/s (pp512, batch 512)
Model
llama-2-7b.Q4_0.gguf (ggml-org, 3.56 GiB, 6.74B params)
Methodology
COMMUNITY-SCOREBOARD (llama.cpp discussion #10879, Vulkan backend, maintainer-curated table). llama-bench -m llama-2-7b.Q4_0.gguf -ngl 99 -fa 0. build 7f76692. pp512 is prompt processing of 512 tokens with no generation, one request, NOT an aggregate. Re-read of the discussion page on 2026-10-16.
Measured by
third_party
Reproducible
yes
notes
Vulkan scoreboard row. memory config unknown; see accelerator notes pp512 tracks compute more than bandwidth.
Notes
Vulkan scoreboard row. memory config unknown; see accelerator notes pp512 tracks compute more than bandwidth.