llama.cpp Metal on Apple M6 (Mac mini, 12-core GPU, 32 GB): llama 7B Q8_0 (6.67 GiB, 6.74B) tg128 (discussion #4167)
21.01 tok/s (tg128, per-request, batch 1)
Fields
id
benchmarks/llamacpp-metal-m6-q8-0-tg128Metric
decode_tok_s
Value
21.01
Unit
tok/s (tg128, per-request, batch 1)
Model
llama 7B Q8_0 (6.67 GiB, 6.74B)
Methodology
COMMUNITY llama-bench (llama.cpp discussion #4167, comment by @jhen0409 dated 2026-10-01). Mac mini M6, 12-core GPU, 32 GB unified memory, reporter-stated bandwidth 170 GB/s, macOS 27.0.1. Backend BLAS,MTL, 2 threads. Build commit 0c1e570. Mean of the default repeats. Per-request batch-1, NOT aggregate. Model: llama 7B Q8_0 (6.67 GiB, 6.74B).
Measured by
third_party
Reproducible
yes
notes
First measured coverage for the base M6. The pinned scoreboard table lists the same figures under commit c1d0e7a; the reporter's own paste cites build 0c1e570, which this record uses.
Notes
First measured coverage for the base M6. The pinned scoreboard table lists the same figures under commit c1d0e7a; the reporter's own paste cites build 0c1e570, which this record uses.