llama.cpp Vulkan/MoltenVK on Apple M3 Ultra: Llama-2-7B Q4_0 noFA pp512 tok/s
1116.83 tok/s (pp512)
Fields
id
benchmarks/llamacpp-vulkan-m3-ultra-llama27b-q40-nofa-pp512Metric
prefill_tok_s
Value
1,116.83
Unit
tok/s (pp512)
Model
llama-2-7b.Q4_0.gguf (TheBloke, 3.56 GiB, 6.74B params)
Methodology
Same MoltenVK run: pp512 1116.83.
Measured by
third_party
Reproducible
yes