llama.cpp Vulkan Intel Arc B580 llama-2-7b Q4_0 tg128 FA
72.0 tok/s (tg128)
Fields
id
benchmarks/llamacpp-vulkan-b580-llama27b-q40-fa-tg128Metric
decode_tok_s
Value
72
Unit
tok/s (tg128)
Model
llama-2-7b.Q4_0.gguf (TheBloke, 3.56 GiB, 6.74B params)
Methodology
COMMUNITY-SCOREBOARD (llama.cpp discussion #10879, maintainer-curated Vulkan backend). llama-bench llama-2-7b.Q4_0.gguf (TheBloke, 3.56 GiB, 6.74B params), pp512 + tg128 batch-1, ngl=99 full offload, Vulkan. Build 7f76692. Chip Intel Arc B580. Per-request batch-1.
Measured by
third_party
Reproducible
yes