LLaMA family 7B / F16 / Mac mini M2 Metal b1550 / PP512 TG128 / exact base and artifact unknown
on M2 24GB · llama.cpp b1550 (8e672efe) / Metal
Summary
User reports a LLaMA-family 7B model at 6.7 t/s generation and 201.3 t/s prompt processing on a Mac mini M2 with 24 GB unified RAM.
Setup is llama.cpp build 1550 with F16 weights and F16 KV cache, Metal backend with ngl 99 on one GPU.
The figures are native llama-bench PP512 and TG128 results, 201.34 ± 0.21 t/s and 6.72 ± 0.01 t/s, independent synthetic prompt and generation tests rather than a 512-token prompt followed by a 128-token answer.