← Back to community benchmarks

Harmonic-Hermes-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-04-17

Performance

1k

tokens

337.4

PP tok/s

50.1

TG tok/s

3035

TTFT (ms)

5.8

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	337.4	50.1	5.8 GB	current
4k	341.8	46.9	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.1	1.00×
2×	76.9	1.53×
4×	83.1	1.66×