← Back to community benchmarks

Qwen3.6-27B

M5 Max (40c) · 128 GB · 8bit · 2026-04-26

Performance

4k

tokens

857.0

PP tok/s

17.9

TG tok/s

4780

TTFT (ms)

29.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	715.1	18.3	28.3 GB	view
4k	857.0	17.9	29.8 GB	current
8k	820.0	17.5	30.4 GB	view
16k	732.1	16.4	31.7 GB	view
32k	677.2	15.2	34.2 GB	view
64k	589.8	13.1	39.2 GB	view
128k	435.0	9.0	49.6 GB	view