← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M1 Max (32c) · 64 GB · 6bit · 2026-05-23

Performance

32k

tokens

80.0

PP tok/s

11.5

TG tok/s

409410

TTFT (ms)

25.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9

macOS macOS 15.7.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	84.3	13.8	22.0 GB	view
4k	86.1	13.7	22.2 GB	view
8k	85.6	14.0	22.9 GB	view
16k	83.7	12.6	23.9 GB	view
32k	80.0	11.5	25.8 GB	current
64k	64.9	6.8	28.9 GB	view