← Back to community benchmarks

Qwen3.6-27B

M2 Max (38c) · 96 GB · 4bit · 2026-05-05

Performance

16k

tokens

95.9

PP tok/s

12.2

TG tok/s

170783

TTFT (ms)

19.8

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	102.7	42.5	19.5 GB	view
4k	98.7	13.8	17.3 GB	view
8k	98.6	12.5	18.3 GB	view
16k	95.9	12.2	19.8 GB	current
32k	93.0	11.3	22.8 GB	view