← Back to community benchmarks

Ornstein3.6-27B-MTP-NSC-ACE-SABER-oQ6-mtp

M4 Pro (20c) · 48 GB · 6bit · 2026-05-18

Performance

8k

tokens

121.6

PP tok/s

10.5

TG tok/s

67386

TTFT (ms)

25.1

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	120.7	10.8	22.6 GB	view
4k	123.2	10.6	24.0 GB	view
8k	121.6	10.5	25.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.8	1.00×
2×	17.9	1.66×
4×	18.6	1.72×
8×	19.6	1.81×