← Back to community benchmarks

Qwen3.6-27B

M1 Max (32c) · 64 GB · 4bit · 2026-04-26

Performance

1k

tokens

80.7

PP tok/s

14.8

TG tok/s

12696

TTFT (ms)

19.5

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.7rc2

macOS macOS 15.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	80.7	14.8	19.5 GB	current
4k	82.8	18.2	17.3 GB	view
8k	87.0	16.6	17.9 GB	view