← Back to community benchmarks

Qwen3.6-27B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-04-28

Performance

8k

tokens

675.6

PP tok/s

22.7

TG tok/s

12126

TTFT (ms)

25.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	751.9	103.0	26.7 GB	view
4k	712.0	93.1	29.0 GB	view
8k	675.6	22.7	25.1 GB	current
16k	751.6	21.5	26.3 GB	view
32k	690.8	19.1	28.8 GB	view