← Back to community benchmarks

Qwen3.6-27B-mtp

M3 Ultra (60c) · 96 GB · 8bit · 2026-04-29

Performance

16k

tokens

304.7

PP tok/s

19.4

TG tok/s

53773

TTFT (ms)

30.9

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	281.8	97.7	31.2 GB	view
4k	266.9	22.1	29.0 GB	view
8k	312.6	21.3	29.6 GB	view
16k	304.7	19.4	30.9 GB	current
32k	287.4	16.8	33.4 GB	view