← Back to community benchmarks

Harmonic-Hermes-9B

M4 Pro (16c) · 24 GB · 8bit · 2026-04-17

Performance

4k

tokens

349.7

PP tok/s

27.2

TG tok/s

11714

TTFT (ms)

10.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	317.4	27.8	9.9 GB	view
4k	349.7	27.2	10.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.8	1.00×
2×	49.1	1.77×
4×	59.3	2.13×