← Back to community benchmarks

Qwen3.6-27BoQ4

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

Performance

8k

tokens

112.6

PP tok/s

17.1

TG tok/s

72734

TTFT (ms)

18.7

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 8,192

Performance by Context Length

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