← Back to community benchmarks

Harmonic-Hermes-9BoQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-29

Performance

1k

tokens

1,901

PP tok/s

94.7

TG tok/s

539

TTFT (ms)

6.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,901	94.7	6.1 GB	current
4k	2,786	91.4	6.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	94.7	1.00×
2×	168.2	1.78×
4×	230.5	2.43×