← Back to community benchmarks

Qwen3.6-27B

M5 Max (40c) · 128 GB · 8bit · 2026-07-23

Performance

4k

tokens

824.0

PP tok/s

16.9

TG tok/s

4971

TTFT (ms)

29.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	789.7	16.8	28.4 GB	view
4k	824.0	16.9	29.9 GB	current
8k	762.0	16.7	30.9 GB	view
16k	671.8	16.2	32.4 GB	view
32k	604.3	15.7	35.4 GB	view
64k	508.9	14.9	41.4 GB	view
128k	385.3	13.2	53.8 GB	view