← Back to community benchmarks

Qwen3.6-27B-mtp

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

Performance

8k

tokens

312.6

PP tok/s

21.3

TG tok/s

26210

TTFT (ms)

29.6

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 8,192

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	current
16k	304.7	19.4	30.9 GB	view
32k	287.4	16.8	33.4 GB	view