← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-23

Performance

16k

tokens

663.8

PP tok/s

25.6

TG tok/s

24682

TTFT (ms)

32.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	716.7	25.9	28.8 GB	view
4k	717.5	29.8	30.3 GB	view
8k	685.2	27.5	31.3 GB	view
16k	663.8	25.6	32.8 GB	current
32k	607.5	24.6	35.8 GB	view