← Back to community benchmarks

Qwen3.6-27BoQ4

M1 Max (24c) · 32 GB · 4bit · 2026-04-24

Performance

1k

tokens

110.7

PP tok/s

18.8

TG tok/s

9250

TTFT (ms)

16.6

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	110.7	18.8	16.6 GB	current
8k	112.6	17.1	18.7 GB	view
32k	104.6	9.5	22.4 GB	view